From b22cc1d295f4e67f4bd7ab5c1c7168ad4a91280a Mon Sep 17 00:00:00 2001
From: Leon Chen <leon@md.ai>
Date: Sat, 27 Aug 2016 00:45:42 -0400
Subject: [PATCH] add ZeroPadding1D/2D/3D layers, with tests

---
 index.html                                  |   6 +
 notebooks/convolutional/ZeroPadding1D.ipynb | 166 +++++++++++++
 notebooks/convolutional/ZeroPadding2D.ipynb | 256 ++++++++++++++++++++
 notebooks/convolutional/ZeroPadding3D.ipynb | 256 ++++++++++++++++++++
 src/layers/convolutional/ZeroPadding1D.js   |  34 +++
 src/layers/convolutional/ZeroPadding2D.js   |  56 +++++
 src/layers/convolutional/ZeroPadding3D.js   |  62 +++++
 src/layers/convolutional/index.js           |   8 +-
 test/convolutional/ZeroPadding1D.js         |  48 ++++
 test/convolutional/ZeroPadding2D.js         |  82 +++++++
 test/convolutional/ZeroPadding3D.js         |  82 +++++++
 test/convolutional/data_ZeroPadding1D.js    |  30 +++
 test/convolutional/data_ZeroPadding2D.js    |  50 ++++
 test/convolutional/data_ZeroPadding3D.js    |  50 ++++
 14 files changed, 1185 insertions(+), 1 deletion(-)
 create mode 100644 notebooks/convolutional/ZeroPadding1D.ipynb
 create mode 100644 notebooks/convolutional/ZeroPadding2D.ipynb
 create mode 100644 notebooks/convolutional/ZeroPadding3D.ipynb
 create mode 100644 src/layers/convolutional/ZeroPadding1D.js
 create mode 100644 src/layers/convolutional/ZeroPadding2D.js
 create mode 100644 src/layers/convolutional/ZeroPadding3D.js
 create mode 100644 test/convolutional/ZeroPadding1D.js
 create mode 100644 test/convolutional/ZeroPadding2D.js
 create mode 100644 test/convolutional/ZeroPadding3D.js
 create mode 100644 test/convolutional/data_ZeroPadding1D.js
 create mode 100644 test/convolutional/data_ZeroPadding2D.js
 create mode 100644 test/convolutional/data_ZeroPadding3D.js

diff --git a/index.html b/index.html
index 1bef3ab..eafa664 100644
--- a/index.html
+++ b/index.html
@@ -56,6 +56,12 @@
   <script src="/test/convolutional/UpSampling2D.js"></script>
   <script src="/test/convolutional/data_UpSampling3D.js"></script>
   <script src="/test/convolutional/UpSampling3D.js"></script>
+  <script src="/test/convolutional/data_ZeroPadding1D.js"></script>
+  <script src="/test/convolutional/ZeroPadding1D.js"></script>
+  <script src="/test/convolutional/data_ZeroPadding2D.js"></script>
+  <script src="/test/convolutional/ZeroPadding2D.js"></script>
+  <script src="/test/convolutional/data_ZeroPadding3D.js"></script>
+  <script src="/test/convolutional/ZeroPadding3D.js"></script>
 
   <script>
     // mocha.checkLeaks();
diff --git a/notebooks/convolutional/ZeroPadding1D.ipynb b/notebooks/convolutional/ZeroPadding1D.ipynb
new file mode 100644
index 0000000..1a763b5
--- /dev/null
+++ b/notebooks/convolutional/ZeroPadding1D.ipynb
@@ -0,0 +1,166 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from keras.models import Model\n",
+    "from keras.layers import Input\n",
+    "from keras.layers.convolutional import ZeroPadding1D\n",
+    "from keras import backend as K"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def format_decimal(arr, places=6):\n",
+    "    return [round(x * 10**places) / 10**places for x in arr]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### ZeroPadding1D"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding1D.0] padding 1 on 3x5 input**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (3, 5)\n",
+      "in: [-0.412987, -0.139246, 0.567466, -0.512174, -0.33603, 0.585584, 0.453472, 0.942013, -0.609538, -0.894302, 0.711927, -0.126057, 0.677549, 0.676991, 0.471487]\n",
+      "out shape: (5, 5)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, -0.412987, -0.139246, 0.567466, -0.512174, -0.33603, 0.585584, 0.453472, 0.942013, -0.609538, -0.894302, 0.711927, -0.126057, 0.677549, 0.676991, 0.471487, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (3, 5)\n",
+    "L = ZeroPadding1D(padding=1)\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(240)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding1D.0] padding 3 on 4x4 input**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (4, 4)\n",
+      "in: [0.229895, 0.156613, -0.66952, -0.996975, 0.45773, 0.684298, -0.999213, 0.276751, -0.484373, -0.506163, 0.353904, 0.513668, -0.981594, 0.78914, 0.603978, 0.204066]\n",
+      "out shape: (10, 4)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.229895, 0.156613, -0.66952, -0.996975, 0.45773, 0.684298, -0.999213, 0.276751, -0.484373, -0.506163, 0.353904, 0.513668, -0.981594, 0.78914, 0.603978, 0.204066, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (4, 4)\n",
+    "L = ZeroPadding1D(padding=3)\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(241)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/convolutional/ZeroPadding2D.ipynb b/notebooks/convolutional/ZeroPadding2D.ipynb
new file mode 100644
index 0000000..0f7001d
--- /dev/null
+++ b/notebooks/convolutional/ZeroPadding2D.ipynb
@@ -0,0 +1,256 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from keras.models import Model\n",
+    "from keras.layers import Input\n",
+    "from keras.layers.convolutional import ZeroPadding2D\n",
+    "from keras import backend as K"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def format_decimal(arr, places=6):\n",
+    "    return [round(x * 10**places) / 10**places for x in arr]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### ZeroPadding2D"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding2D.0] padding (1,1) on 3x5x2 input, dim_ordering=tf**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (3, 5, 2)\n",
+      "in: [-0.570441, -0.454673, -0.285321, 0.237249, 0.282682, 0.428035, 0.160547, -0.332203, 0.546391, 0.272735, 0.010827, -0.763164, -0.442696, 0.381948, -0.676994, 0.753553, -0.031788, 0.915329, -0.738844, 0.269075, 0.434091, 0.991585, -0.944288, 0.258834, 0.162138, 0.565201, -0.492094, 0.170854, -0.139788, -0.710674]\n",
+      "out shape: (5, 7, 2)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.570441, -0.454673, -0.285321, 0.237249, 0.282682, 0.428035, 0.160547, -0.332203, 0.546391, 0.272735, 0.0, 0.0, 0.0, 0.0, 0.010827, -0.763164, -0.442696, 0.381948, -0.676994, 0.753553, -0.031788, 0.915329, -0.738844, 0.269075, 0.0, 0.0, 0.0, 0.0, 0.434091, 0.991585, -0.944288, 0.258834, 0.162138, 0.565201, -0.492094, 0.170854, -0.139788, -0.710674, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (3, 5, 2)\n",
+    "L = ZeroPadding2D(padding=(1, 1), dim_ordering='tf')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(250)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding2D.1] padding (1,1) on 3x5x2 input, dim_ordering=th**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (3, 5, 2)\n",
+      "in: [-0.570441, -0.454673, -0.285321, 0.237249, 0.282682, 0.428035, 0.160547, -0.332203, 0.546391, 0.272735, 0.010827, -0.763164, -0.442696, 0.381948, -0.676994, 0.753553, -0.031788, 0.915329, -0.738844, 0.269075, 0.434091, 0.991585, -0.944288, 0.258834, 0.162138, 0.565201, -0.492094, 0.170854, -0.139788, -0.710674]\n",
+      "out shape: (3, 7, 4)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, -0.570441, -0.454673, 0.0, 0.0, -0.285321, 0.237249, 0.0, 0.0, 0.282682, 0.428035, 0.0, 0.0, 0.160547, -0.332203, 0.0, 0.0, 0.546391, 0.272735, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.010827, -0.763164, 0.0, 0.0, -0.442696, 0.381948, 0.0, 0.0, -0.676994, 0.753553, 0.0, 0.0, -0.031788, 0.915329, 0.0, 0.0, -0.738844, 0.269075, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.434091, 0.991585, 0.0, 0.0, -0.944288, 0.258834, 0.0, 0.0, 0.162138, 0.565201, 0.0, 0.0, -0.492094, 0.170854, 0.0, 0.0, -0.139788, -0.710674, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (3, 5, 2)\n",
+    "L = ZeroPadding2D(padding=(1, 1), dim_ordering='th')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(250)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding2D.2] padding (3,2) on 2x6x4 input, dim_ordering=tf**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (2, 6, 4)\n",
+      "in: [-0.989173, -0.133618, -0.505338, 0.023259, 0.503982, -0.303769, -0.436321, 0.793911, 0.416102, 0.806405, -0.098342, -0.738022, -0.982676, 0.805073, 0.741244, -0.941634, -0.253526, -0.136544, -0.295772, 0.207565, -0.517246, -0.686963, -0.176235, -0.354111, -0.862411, -0.969822, 0.200074, 0.290718, -0.038623, 0.294839, 0.247968, 0.557946, -0.455596, 0.6624, 0.879529, -0.466772, 0.40423, 0.213794, 0.645662, -0.044634, -0.552595, 0.771242, -0.131944, -0.172725, 0.700856, -0.001994, 0.606737, -0.593306]\n",
+      "out shape: (8, 10, 4)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.989173, -0.133618, -0.505338, 0.023259, 0.503982, -0.303769, -0.436321, 0.793911, 0.416102, 0.806405, -0.098342, -0.738022, -0.982676, 0.805073, 0.741244, -0.941634, -0.253526, -0.136544, -0.295772, 0.207565, -0.517246, -0.686963, -0.176235, -0.354111, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.862411, -0.969822, 0.200074, 0.290718, -0.038623, 0.294839, 0.247968, 0.557946, -0.455596, 0.6624, 0.879529, -0.466772, 0.40423, 0.213794, 0.645662, -0.044634, -0.552595, 0.771242, -0.131944, -0.172725, 0.700856, -0.001994, 0.606737, -0.593306, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (2, 6, 4)\n",
+    "L = ZeroPadding2D(padding=(3, 2), dim_ordering='tf')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(252)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding2D.3] padding (3,2) on 2x6x4 input, dim_ordering=th**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (2, 6, 4)\n",
+      "in: [-0.989173, -0.133618, -0.505338, 0.023259, 0.503982, -0.303769, -0.436321, 0.793911, 0.416102, 0.806405, -0.098342, -0.738022, -0.982676, 0.805073, 0.741244, -0.941634, -0.253526, -0.136544, -0.295772, 0.207565, -0.517246, -0.686963, -0.176235, -0.354111, -0.862411, -0.969822, 0.200074, 0.290718, -0.038623, 0.294839, 0.247968, 0.557946, -0.455596, 0.6624, 0.879529, -0.466772, 0.40423, 0.213794, 0.645662, -0.044634, -0.552595, 0.771242, -0.131944, -0.172725, 0.700856, -0.001994, 0.606737, -0.593306]\n",
+      "out shape: (2, 12, 8)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.989173, -0.133618, -0.505338, 0.023259, 0.0, 0.0, 0.0, 0.0, 0.503982, -0.303769, -0.436321, 0.793911, 0.0, 0.0, 0.0, 0.0, 0.416102, 0.806405, -0.098342, -0.738022, 0.0, 0.0, 0.0, 0.0, -0.982676, 0.805073, 0.741244, -0.941634, 0.0, 0.0, 0.0, 0.0, -0.253526, -0.136544, -0.295772, 0.207565, 0.0, 0.0, 0.0, 0.0, -0.517246, -0.686963, -0.176235, -0.354111, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.862411, -0.969822, 0.200074, 0.290718, 0.0, 0.0, 0.0, 0.0, -0.038623, 0.294839, 0.247968, 0.557946, 0.0, 0.0, 0.0, 0.0, -0.455596, 0.6624, 0.879529, -0.466772, 0.0, 0.0, 0.0, 0.0, 0.40423, 0.213794, 0.645662, -0.044634, 0.0, 0.0, 0.0, 0.0, -0.552595, 0.771242, -0.131944, -0.172725, 0.0, 0.0, 0.0, 0.0, 0.700856, -0.001994, 0.606737, -0.593306, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (2, 6, 4)\n",
+    "L = ZeroPadding2D(padding=(3, 2), dim_ordering='th')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(252)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/convolutional/ZeroPadding3D.ipynb b/notebooks/convolutional/ZeroPadding3D.ipynb
new file mode 100644
index 0000000..aa67a96
--- /dev/null
+++ b/notebooks/convolutional/ZeroPadding3D.ipynb
@@ -0,0 +1,256 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from keras.models import Model\n",
+    "from keras.layers import Input\n",
+    "from keras.layers.convolutional import ZeroPadding3D\n",
+    "from keras import backend as K"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def format_decimal(arr, places=6):\n",
+    "    return [round(x * 10**places) / 10**places for x in arr]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### ZeroPadding3D"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding3D.0] padding (1,1,1) on 3x5x2x2 input, dim_ordering=tf**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (3, 5, 2, 2)\n",
+      "in: [-0.806777, -0.564841, -0.481331, 0.559626, 0.274958, -0.659222, -0.178541, 0.689453, -0.028873, 0.053859, -0.446394, -0.53406, 0.776897, -0.700858, -0.802179, -0.616515, 0.718677, 0.303042, -0.080606, -0.850593, -0.795971, 0.860487, -0.90685, 0.89858, 0.617251, 0.334305, -0.351137, -0.642574, 0.108974, -0.993964, 0.051085, -0.372012, 0.843766, 0.088025, -0.598662, 0.789035, -0.971233, -0.917609, 0.10035, -0.993908, 0.001303, 0.151006, -0.222302, -0.462642, 0.318882, 0.910461, -0.951606, -0.628088, 0.858834, 0.18648, 0.005839, -0.976863, -0.602595, -0.907466, 0.537085, 0.254335, -0.624879, -0.26462, -0.597274, 0.717515]\n",
+      "out shape: (5, 7, 4, 2)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.806777, -0.564841, -0.481331, 0.559626, 0.0, 0.0, 0.0, 0.0, 0.274958, -0.659222, -0.178541, 0.689453, 0.0, 0.0, 0.0, 0.0, -0.028873, 0.053859, -0.446394, -0.53406, 0.0, 0.0, 0.0, 0.0, 0.776897, -0.700858, -0.802179, -0.616515, 0.0, 0.0, 0.0, 0.0, 0.718677, 0.303042, -0.080606, -0.850593, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.795971, 0.860487, -0.90685, 0.89858, 0.0, 0.0, 0.0, 0.0, 0.617251, 0.334305, -0.351137, -0.642574, 0.0, 0.0, 0.0, 0.0, 0.108974, -0.993964, 0.051085, -0.372012, 0.0, 0.0, 0.0, 0.0, 0.843766, 0.088025, -0.598662, 0.789035, 0.0, 0.0, 0.0, 0.0, -0.971233, -0.917609, 0.10035, -0.993908, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.001303, 0.151006, -0.222302, -0.462642, 0.0, 0.0, 0.0, 0.0, 0.318882, 0.910461, -0.951606, -0.628088, 0.0, 0.0, 0.0, 0.0, 0.858833, 0.18648, 0.005839, -0.976863, 0.0, 0.0, 0.0, 0.0, -0.602595, -0.907466, 0.537085, 0.254335, 0.0, 0.0, 0.0, 0.0, -0.624879, -0.26462, -0.597274, 0.717515, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (3, 5, 2, 2)\n",
+    "L = ZeroPadding3D(padding=(1, 1, 1), dim_ordering='tf')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(260)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding3D.1] padding (1,1,1) on 3x5x2x2 input, dim_ordering=th**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (3, 5, 2, 2)\n",
+      "in: [0.601872, -0.028379, 0.654213, 0.217731, -0.864161, 0.422013, 0.888312, -0.714141, -0.184753, 0.224845, -0.221123, -0.847943, -0.511334, -0.871723, -0.597589, -0.889034, -0.544887, -0.004798, 0.406639, -0.35285, 0.648562, 0.325102, -0.691014, -0.77342, -0.290393, -0.724779, 0.282119, 0.149588, 0.189558, -0.216989, -0.959622, -0.6309, -0.935622, -0.799247, -0.434939, -0.46504, -0.354178, 0.299364, -0.141294, 0.7451, 0.479026, -0.401207, -0.100649, 0.210378, 0.274347, 0.18857, -0.806871, -0.319347, -0.340714, 0.158351, -0.628744, -0.831363, -0.438345, 0.476498, 0.078437, 0.440929, -0.104442, -0.298102, -0.71911, -0.639047]\n",
+      "out shape: (3, 7, 4, 4)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.601872, -0.028379, 0.0, 0.0, 0.654213, 0.217731, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.864161, 0.422013, 0.0, 0.0, 0.888312, -0.714141, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.184753, 0.224845, 0.0, 0.0, -0.221123, -0.847943, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.511334, -0.871723, 0.0, 0.0, -0.597589, -0.889034, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.544887, -0.004798, 0.0, 0.0, 0.406639, -0.35285, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.648562, 0.325102, 0.0, 0.0, -0.691014, -0.77342, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.290393, -0.724779, 0.0, 0.0, 0.282119, 0.149588, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.189558, -0.216989, 0.0, 0.0, -0.959622, -0.6309, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.935622, -0.799247, 0.0, 0.0, -0.434939, -0.46504, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.354178, 0.299364, 0.0, 0.0, -0.141294, 0.7451, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.479026, -0.401207, 0.0, 0.0, -0.100649, 0.210378, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.274347, 0.18857, 0.0, 0.0, -0.806871, -0.319347, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.340714, 0.158351, 0.0, 0.0, -0.628744, -0.831363, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.438345, 0.476498, 0.0, 0.0, 0.078437, 0.440929, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.104442, -0.298102, 0.0, 0.0, -0.71911, -0.639047, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (3, 5, 2, 2)\n",
+    "L = ZeroPadding3D(padding=(1, 1, 1), dim_ordering='th')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(261)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding3D.2] padding (3,2,2) on 3x2x1x4 input, dim_ordering=tf**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (3, 2, 1, 4)\n",
+      "in: [-0.215694, 0.441215, 0.116911, 0.53299, 0.883562, -0.535525, -0.869764, -0.596287, 0.576428, -0.689083, -0.132924, -0.129935, -0.17672, -0.29097, 0.590914, 0.992098, 0.908965, -0.170202, 0.640203, 0.178644, 0.866749, -0.545566, -0.827072, 0.420342]\n",
+      "out shape: (9, 6, 5, 4)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.215694, 0.441215, 0.116911, 0.53299, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.883562, -0.535525, -0.869764, -0.596287, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.576428, -0.689083, -0.132924, -0.129935, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.17672, -0.29097, 0.590914, 0.992098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.908965, -0.170202, 0.640203, 0.178644, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.866749, -0.545566, -0.827072, 0.420342, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (3, 2, 1, 4)\n",
+    "L = ZeroPadding3D(padding=(3, 2, 2), dim_ordering='tf')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(262)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**[convolutional.ZeroPadding3D.3] padding (3,2,2) on 3x2x1x4 input, dim_ordering=th**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "in shape: (3, 2, 1, 4)\n",
+      "in: [-0.215694, 0.441215, 0.116911, 0.53299, 0.883562, -0.535525, -0.869764, -0.596287, 0.576428, -0.689083, -0.132924, -0.129935, -0.17672, -0.29097, 0.590914, 0.992098, 0.908965, -0.170202, 0.640203, 0.178644, 0.866749, -0.545566, -0.827072, 0.420342]\n",
+      "out shape: (3, 8, 5, 8)\n",
+      "out: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.215694, 0.441215, 0.116911, 0.53299, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.883562, -0.535525, -0.869764, -0.596287, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.576428, -0.689083, -0.132924, -0.129935, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.17672, -0.29097, 0.590914, 0.992098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.908965, -0.170202, 0.640203, 0.178644, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.866749, -0.545566, -0.827072, 0.420342, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (3, 2, 1, 4)\n",
+    "L = ZeroPadding3D(padding=(3, 2, 2), dim_ordering='th')\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = L(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "np.random.seed(262)\n",
+    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
+    "print('')\n",
+    "print('in shape:', data_in_shape)\n",
+    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
+    "result = model.predict(np.array([data_in]))\n",
+    "print('out shape:', result[0].shape)\n",
+    "print('out:', format_decimal(result[0].ravel().tolist()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/src/layers/convolutional/ZeroPadding1D.js b/src/layers/convolutional/ZeroPadding1D.js
new file mode 100644
index 0000000..3da0b9f
--- /dev/null
+++ b/src/layers/convolutional/ZeroPadding1D.js
@@ -0,0 +1,34 @@
+import Layer from '../../engine/Layer'
+import Tensor from '../../Tensor'
+import ops from 'ndarray-ops'
+
+/**
+ * ZeroPadding1D layer class
+ */
+export default class ZeroPadding1D extends Layer {
+  /**
+   * Creates a ZeroPadding1D activation layer
+   * @param {number} padding - length of padding
+   */
+  constructor (padding = 1, attrs = {}) {
+    super(attrs)
+    this.padding = padding
+  }
+
+  /**
+   * Method for layer computational logic
+   * @param {Tensor} x
+   * @returns {Tensor} x
+   */
+  call = x => {
+    const inputShape = x.tensor.shape
+    const outputShape = [inputShape[0] + this.padding * 2, inputShape[1]]
+    let y = new Tensor([], outputShape)
+    ops.assign(
+      y.tensor.hi(inputShape[0] + this.padding, inputShape[1]).lo(this.padding, 0),
+      x.tensor
+    )
+    x.tensor = y.tensor
+    return x
+  }
+}
diff --git a/src/layers/convolutional/ZeroPadding2D.js b/src/layers/convolutional/ZeroPadding2D.js
new file mode 100644
index 0000000..94db726
--- /dev/null
+++ b/src/layers/convolutional/ZeroPadding2D.js
@@ -0,0 +1,56 @@
+import Layer from '../../engine/Layer'
+import Tensor from '../../Tensor'
+import ops from 'ndarray-ops'
+
+/**
+ * ZeroPadding2D layer class
+ */
+export default class ZeroPadding2D extends Layer {
+  /**
+   * Creates a ZeroPadding2D activation layer
+   * @param {number} padding - size of padding
+   */
+  constructor (padding = [1, 1], attrs = {}) {
+    super(attrs)
+    const {
+      dimOrdering = 'tf'
+    } = attrs
+
+    this.padding = padding
+    this.dimOrdering = dimOrdering
+  }
+
+  /**
+   * Method for layer computational logic
+   * @param {Tensor} x
+   * @returns {Tensor} x
+   */
+  call = x => {
+    // convert to tf ordering
+    if (this.dimOrdering === 'th') {
+      x.tensor = x.tensor.transpose(1, 2, 0)
+    }
+
+    const inputShape = x.tensor.shape
+    const outputShape = [
+      inputShape[0] + this.padding[0] * 2,
+      inputShape[1] + this.padding[1] * 2,
+      inputShape[2]
+    ]
+    let y = new Tensor([], outputShape)
+    ops.assign(
+      y.tensor
+        .hi(inputShape[0] + this.padding[0], inputShape[1] + this.padding[1], inputShape[2])
+        .lo(this.padding[0], this.padding[1], 0),
+      x.tensor
+    )
+    x.tensor = y.tensor
+
+    // convert back to th ordering if necessary
+    if (this.dimOrdering === 'th') {
+      x.tensor = x.tensor.transpose(2, 0, 1)
+    }
+
+    return x
+  }
+}
diff --git a/src/layers/convolutional/ZeroPadding3D.js b/src/layers/convolutional/ZeroPadding3D.js
new file mode 100644
index 0000000..9fde0b3
--- /dev/null
+++ b/src/layers/convolutional/ZeroPadding3D.js
@@ -0,0 +1,62 @@
+import Layer from '../../engine/Layer'
+import Tensor from '../../Tensor'
+import ops from 'ndarray-ops'
+
+/**
+ * ZeroPadding3D layer class
+ */
+export default class ZeroPadding3D extends Layer {
+  /**
+   * Creates a ZeroPadding3D activation layer
+   * @param {number} padding - size of padding
+   */
+  constructor (padding = [1, 1, 1], attrs = {}) {
+    super(attrs)
+    const {
+      dimOrdering = 'tf'
+    } = attrs
+
+    this.padding = padding
+    this.dimOrdering = dimOrdering
+  }
+
+  /**
+   * Method for layer computational logic
+   * @param {Tensor} x
+   * @returns {Tensor} x
+   */
+  call = x => {
+    // convert to tf ordering
+    if (this.dimOrdering === 'th') {
+      x.tensor = x.tensor.transpose(1, 2, 3, 0)
+    }
+
+    const inputShape = x.tensor.shape
+    const outputShape = [
+      inputShape[0] + this.padding[0] * 2,
+      inputShape[1] + this.padding[1] * 2,
+      inputShape[2] + this.padding[2] * 2,
+      inputShape[3]
+    ]
+    let y = new Tensor([], outputShape)
+    ops.assign(
+      y.tensor
+        .hi(
+          inputShape[0] + this.padding[0],
+          inputShape[1] + this.padding[1],
+          inputShape[2] + this.padding[2],
+          inputShape[3]
+        )
+        .lo(this.padding[0], this.padding[1], this.padding[2], 0),
+      x.tensor
+    )
+    x.tensor = y.tensor
+
+    // convert back to th ordering if necessary
+    if (this.dimOrdering === 'th') {
+      x.tensor = x.tensor.transpose(3, 0, 1, 2)
+    }
+
+    return x
+  }
+}
diff --git a/src/layers/convolutional/index.js b/src/layers/convolutional/index.js
index b55a7d1..93fe4bf 100644
--- a/src/layers/convolutional/index.js
+++ b/src/layers/convolutional/index.js
@@ -4,6 +4,9 @@ import Convolution3D from './Convolution3D'
 import UpSampling1D from './UpSampling1D'
 import UpSampling2D from './UpSampling2D'
 import UpSampling3D from './UpSampling3D'
+import ZeroPadding1D from './ZeroPadding1D'
+import ZeroPadding2D from './ZeroPadding2D'
+import ZeroPadding3D from './ZeroPadding3D'
 
 export {
   Convolution1D,
@@ -11,5 +14,8 @@ export {
   Convolution3D,
   UpSampling1D,
   UpSampling2D,
-  UpSampling3D
+  UpSampling3D,
+  ZeroPadding1D,
+  ZeroPadding2D,
+  ZeroPadding3D
 }
diff --git a/test/convolutional/ZeroPadding1D.js b/test/convolutional/ZeroPadding1D.js
new file mode 100644
index 0000000..09669ab
--- /dev/null
+++ b/test/convolutional/ZeroPadding1D.js
@@ -0,0 +1,48 @@
+/* eslint-env browser, mocha */
+
+describe('convolutional layer: ZeroPadding1D', function () {
+  const assert = chai.assert
+  const styles = testGlobals.styles
+  const logTime = testGlobals.logTime
+  const stringifyCondensed = testGlobals.stringifyCondensed
+  const approxEquals = KerasJS.testUtils.approxEquals
+  const layers = KerasJS.layers
+
+  before(function () {
+    console.log('\n%cconvolutional layer: ZeroPadding1D', styles.h1)
+  })
+
+  it(`[convolutional.ZeroPadding1D.0] padding 1 on 3x5 input`, function () {
+    const key = `convolutional.ZeroPadding1D.0`
+    console.log(`\n%c[${key}] padding 1 on 3x5 input`, styles.h3)
+    let testLayer = new layers.ZeroPadding1D(1)
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+
+  it(`[convolutional.ZeroPadding1D.1] padding 3 on 4x4 input`, function () {
+    const key = `convolutional.ZeroPadding1D.1`
+    console.log(`\n%c[${key}] padding 3 on 4x4 input`, styles.h3)
+    let testLayer = new layers.ZeroPadding1D(3)
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+})
diff --git a/test/convolutional/ZeroPadding2D.js b/test/convolutional/ZeroPadding2D.js
new file mode 100644
index 0000000..98a5fb0
--- /dev/null
+++ b/test/convolutional/ZeroPadding2D.js
@@ -0,0 +1,82 @@
+/* eslint-env browser, mocha */
+
+describe('convolutional layer: ZeroPadding2D', function () {
+  const assert = chai.assert
+  const styles = testGlobals.styles
+  const logTime = testGlobals.logTime
+  const stringifyCondensed = testGlobals.stringifyCondensed
+  const approxEquals = KerasJS.testUtils.approxEquals
+  const layers = KerasJS.layers
+
+  before(function () {
+    console.log('\n%cconvolutional layer: ZeroPadding2D', styles.h1)
+  })
+
+  it(`[convolutional.ZeroPadding2D.0] padding 1,1 on 3x5x2 input, dimOrdering=tf`, function () {
+    const key = `convolutional.ZeroPadding2D.0`
+    console.log(`\n%c[${key}] padding 1,1 on 3x5x2 input, dimOrdering=tf`, styles.h3)
+    let testLayer = new layers.ZeroPadding2D([1, 1], { dimOrdering: 'tf' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+
+  it(`[convolutional.ZeroPadding2D.1] padding 1,1 on 3x5x2 input, dimOrdering=th`, function () {
+    const key = `convolutional.ZeroPadding2D.1`
+    console.log(`\n%c[${key}] padding 1,1 on 3x5x2 input, dimOrdering=th`, styles.h3)
+    let testLayer = new layers.ZeroPadding2D([1, 1], { dimOrdering: 'th' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+
+  it(`[convolutional.ZeroPadding2D.2] padding 3,2 on 2x6x4 input, dimOrdering=tf`, function () {
+    const key = `convolutional.ZeroPadding2D.2`
+    console.log(`\n%c[${key}] padding 3,2 on 2x6x4 input, dimOrdering=tf`, styles.h3)
+    let testLayer = new layers.ZeroPadding2D([3, 2], { dimOrdering: 'tf' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+
+  it(`[convolutional.ZeroPadding2D.3] padding 3,2 on 2x6x4 input, dimOrdering=th`, function () {
+    const key = `convolutional.ZeroPadding2D.3`
+    console.log(`\n%c[${key}] padding 3,2 on 2x6x4 input, dimOrdering=th`, styles.h3)
+    let testLayer = new layers.ZeroPadding2D([3, 2], { dimOrdering: 'th' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+})
diff --git a/test/convolutional/ZeroPadding3D.js b/test/convolutional/ZeroPadding3D.js
new file mode 100644
index 0000000..03e656e
--- /dev/null
+++ b/test/convolutional/ZeroPadding3D.js
@@ -0,0 +1,82 @@
+/* eslint-env browser, mocha */
+
+describe('convolutional layer: ZeroPadding3D', function () {
+  const assert = chai.assert
+  const styles = testGlobals.styles
+  const logTime = testGlobals.logTime
+  const stringifyCondensed = testGlobals.stringifyCondensed
+  const approxEquals = KerasJS.testUtils.approxEquals
+  const layers = KerasJS.layers
+
+  before(function () {
+    console.log('\n%cconvolutional layer: ZeroPadding3D', styles.h1)
+  })
+
+  it(`[convolutional.ZeroPadding3D.0] padding 1,1,1 on 3x5x2x2 input, dimOrdering=tf`, function () {
+    const key = `convolutional.ZeroPadding3D.0`
+    console.log(`\n%c[${key}] padding 1,1,1 on 3x5x2x2 input, dimOrdering=tf`, styles.h3)
+    let testLayer = new layers.ZeroPadding3D([1, 1, 1], { dimOrdering: 'tf' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+
+  it(`[convolutional.ZeroPadding3D.1] padding 1,1,1 on 3x5x2x2 input, dimOrdering=th`, function () {
+    const key = `convolutional.ZeroPadding3D.1`
+    console.log(`\n%c[${key}] padding 1,1,1 on 3x5x2x2 input, dimOrdering=th`, styles.h3)
+    let testLayer = new layers.ZeroPadding3D([1, 1, 1], { dimOrdering: 'th' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+
+  it(`[convolutional.ZeroPadding3D.2] padding 3,2,2 on 3x2x1x4 input, dimOrdering=tf`, function () {
+    const key = `convolutional.ZeroPadding3D.2`
+    console.log(`\n%c[${key}] padding 3,2,2 on 3x2x1x4 input, dimOrdering=tf`, styles.h3)
+    let testLayer = new layers.ZeroPadding3D([3, 2, 2], { dimOrdering: 'tf' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+
+  it(`[convolutional.ZeroPadding3D.3] padding 3,2,2 on 3x2x1x4 input, dimOrdering=th`, function () {
+    const key = `convolutional.ZeroPadding3D.3`
+    console.log(`\n%c[${key}] padding 3,2,2 on 3x2x1x4 input, dimOrdering=th`, styles.h3)
+    let testLayer = new layers.ZeroPadding3D([3, 2, 2], { dimOrdering: 'th' })
+    let t = new KerasJS.Tensor(TEST_DATA[key].input.data, TEST_DATA[key].input.shape)
+    console.log('%cin', styles.h4, stringifyCondensed(t.tensor))
+    const startTime = performance.now()
+    t = testLayer.call(t)
+    const endTime = performance.now()
+    console.log('%cout', styles.h4, stringifyCondensed(t.tensor))
+    logTime(startTime, endTime)
+    const dataExpected = new Float32Array(TEST_DATA[key].expected.data)
+    const shapeExpected = TEST_DATA[key].expected.shape
+    assert.deepEqual(t.tensor.shape, shapeExpected)
+    assert.isTrue(approxEquals(t.tensor, dataExpected))
+  })
+})
diff --git a/test/convolutional/data_ZeroPadding1D.js b/test/convolutional/data_ZeroPadding1D.js
new file mode 100644
index 0000000..9d4d950
--- /dev/null
+++ b/test/convolutional/data_ZeroPadding1D.js
@@ -0,0 +1,30 @@
+// TEST DATA
+// Keyed by mocha test ID
+// Python code for generating test data can be found in the matching jupyter notebook in folder `notebooks/`.
+
+(function () {
+  var DATA = {
+    'convolutional.ZeroPadding1D.0': {
+      input: {
+        data: [-0.412987, -0.139246, 0.567466, -0.512174, -0.33603, 0.585584, 0.453472, 0.942013, -0.609538, -0.894302, 0.711927, -0.126057, 0.677549, 0.676991, 0.471487],
+        shape: [3, 5]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, -0.412987, -0.139246, 0.567466, -0.512174, -0.33603, 0.585584, 0.453472, 0.942013, -0.609538, -0.894302, 0.711927, -0.126057, 0.677549, 0.676991, 0.471487, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [5, 5]
+      }
+    },
+    'convolutional.ZeroPadding1D.1': {
+      input: {
+        data: [0.229895, 0.156613, -0.66952, -0.996975, 0.45773, 0.684298, -0.999213, 0.276751, -0.484373, -0.506163, 0.353904, 0.513668, -0.981594, 0.78914, 0.603978, 0.204066],
+        shape: [4, 4]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.229895, 0.156613, -0.66952, -0.996975, 0.45773, 0.684298, -0.999213, 0.276751, -0.484373, -0.506163, 0.353904, 0.513668, -0.981594, 0.78914, 0.603978, 0.204066, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [10, 4]
+      }
+    }
+  }
+
+  window.TEST_DATA = Object.assign({}, window.TEST_DATA, DATA)
+})()
diff --git a/test/convolutional/data_ZeroPadding2D.js b/test/convolutional/data_ZeroPadding2D.js
new file mode 100644
index 0000000..96dc136
--- /dev/null
+++ b/test/convolutional/data_ZeroPadding2D.js
@@ -0,0 +1,50 @@
+// TEST DATA
+// Keyed by mocha test ID
+// Python code for generating test data can be found in the matching jupyter notebook in folder `notebooks/`.
+
+(function () {
+  var DATA = {
+    'convolutional.ZeroPadding2D.0': {
+      input: {
+        data: [-0.570441, -0.454673, -0.285321, 0.237249, 0.282682, 0.428035, 0.160547, -0.332203, 0.546391, 0.272735, 0.010827, -0.763164, -0.442696, 0.381948, -0.676994, 0.753553, -0.031788, 0.915329, -0.738844, 0.269075, 0.434091, 0.991585, -0.944288, 0.258834, 0.162138, 0.565201, -0.492094, 0.170854, -0.139788, -0.710674],
+        shape: [3, 5, 2]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.570441, -0.454673, -0.285321, 0.237249, 0.282682, 0.428035, 0.160547, -0.332203, 0.546391, 0.272735, 0.0, 0.0, 0.0, 0.0, 0.010827, -0.763164, -0.442696, 0.381948, -0.676994, 0.753553, -0.031788, 0.915329, -0.738844, 0.269075, 0.0, 0.0, 0.0, 0.0, 0.434091, 0.991585, -0.944288, 0.258834, 0.162138, 0.565201, -0.492094, 0.170854, -0.139788, -0.710674, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [5, 7, 2]
+      }
+    },
+    'convolutional.ZeroPadding2D.1': {
+      input: {
+        data: [-0.570441, -0.454673, -0.285321, 0.237249, 0.282682, 0.428035, 0.160547, -0.332203, 0.546391, 0.272735, 0.010827, -0.763164, -0.442696, 0.381948, -0.676994, 0.753553, -0.031788, 0.915329, -0.738844, 0.269075, 0.434091, 0.991585, -0.944288, 0.258834, 0.162138, 0.565201, -0.492094, 0.170854, -0.139788, -0.710674],
+        shape: [3, 5, 2]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, -0.570441, -0.454673, 0.0, 0.0, -0.285321, 0.237249, 0.0, 0.0, 0.282682, 0.428035, 0.0, 0.0, 0.160547, -0.332203, 0.0, 0.0, 0.546391, 0.272735, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.010827, -0.763164, 0.0, 0.0, -0.442696, 0.381948, 0.0, 0.0, -0.676994, 0.753553, 0.0, 0.0, -0.031788, 0.915329, 0.0, 0.0, -0.738844, 0.269075, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.434091, 0.991585, 0.0, 0.0, -0.944288, 0.258834, 0.0, 0.0, 0.162138, 0.565201, 0.0, 0.0, -0.492094, 0.170854, 0.0, 0.0, -0.139788, -0.710674, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [3, 7, 4]
+      }
+    },
+    'convolutional.ZeroPadding2D.2': {
+      input: {
+        data: [-0.989173, -0.133618, -0.505338, 0.023259, 0.503982, -0.303769, -0.436321, 0.793911, 0.416102, 0.806405, -0.098342, -0.738022, -0.982676, 0.805073, 0.741244, -0.941634, -0.253526, -0.136544, -0.295772, 0.207565, -0.517246, -0.686963, -0.176235, -0.354111, -0.862411, -0.969822, 0.200074, 0.290718, -0.038623, 0.294839, 0.247968, 0.557946, -0.455596, 0.6624, 0.879529, -0.466772, 0.40423, 0.213794, 0.645662, -0.044634, -0.552595, 0.771242, -0.131944, -0.172725, 0.700856, -0.001994, 0.606737, -0.593306],
+        shape: [2, 6, 4]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.989173, -0.133618, -0.505338, 0.023259, 0.503982, -0.303769, -0.436321, 0.793911, 0.416102, 0.806405, -0.098342, -0.738022, -0.982676, 0.805073, 0.741244, -0.941634, -0.253526, -0.136544, -0.295772, 0.207565, -0.517246, -0.686963, -0.176235, -0.354111, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.862411, -0.969822, 0.200074, 0.290718, -0.038623, 0.294839, 0.247968, 0.557946, -0.455596, 0.6624, 0.879529, -0.466772, 0.40423, 0.213794, 0.645662, -0.044634, -0.552595, 0.771242, -0.131944, -0.172725, 0.700856, -0.001994, 0.606737, -0.593306, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [8, 10, 4]
+      }
+    },
+    'convolutional.ZeroPadding2D.3': {
+      input: {
+        data: [-0.989173, -0.133618, -0.505338, 0.023259, 0.503982, -0.303769, -0.436321, 0.793911, 0.416102, 0.806405, -0.098342, -0.738022, -0.982676, 0.805073, 0.741244, -0.941634, -0.253526, -0.136544, -0.295772, 0.207565, -0.517246, -0.686963, -0.176235, -0.354111, -0.862411, -0.969822, 0.200074, 0.290718, -0.038623, 0.294839, 0.247968, 0.557946, -0.455596, 0.6624, 0.879529, -0.466772, 0.40423, 0.213794, 0.645662, -0.044634, -0.552595, 0.771242, -0.131944, -0.172725, 0.700856, -0.001994, 0.606737, -0.593306],
+        shape: [2, 6, 4]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.989173, -0.133618, -0.505338, 0.023259, 0.0, 0.0, 0.0, 0.0, 0.503982, -0.303769, -0.436321, 0.793911, 0.0, 0.0, 0.0, 0.0, 0.416102, 0.806405, -0.098342, -0.738022, 0.0, 0.0, 0.0, 0.0, -0.982676, 0.805073, 0.741244, -0.941634, 0.0, 0.0, 0.0, 0.0, -0.253526, -0.136544, -0.295772, 0.207565, 0.0, 0.0, 0.0, 0.0, -0.517246, -0.686963, -0.176235, -0.354111, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.862411, -0.969822, 0.200074, 0.290718, 0.0, 0.0, 0.0, 0.0, -0.038623, 0.294839, 0.247968, 0.557946, 0.0, 0.0, 0.0, 0.0, -0.455596, 0.6624, 0.879529, -0.466772, 0.0, 0.0, 0.0, 0.0, 0.40423, 0.213794, 0.645662, -0.044634, 0.0, 0.0, 0.0, 0.0, -0.552595, 0.771242, -0.131944, -0.172725, 0.0, 0.0, 0.0, 0.0, 0.700856, -0.001994, 0.606737, -0.593306, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [2, 12, 8]
+      }
+    }
+  }
+
+  window.TEST_DATA = Object.assign({}, window.TEST_DATA, DATA)
+})()
diff --git a/test/convolutional/data_ZeroPadding3D.js b/test/convolutional/data_ZeroPadding3D.js
new file mode 100644
index 0000000..4283f27
--- /dev/null
+++ b/test/convolutional/data_ZeroPadding3D.js
@@ -0,0 +1,50 @@
+// TEST DATA
+// Keyed by mocha test ID
+// Python code for generating test data can be found in the matching jupyter notebook in folder `notebooks/`.
+
+(function () {
+  var DATA = {
+    'convolutional.ZeroPadding3D.0': {
+      input: {
+        data: [-0.806777, -0.564841, -0.481331, 0.559626, 0.274958, -0.659222, -0.178541, 0.689453, -0.028873, 0.053859, -0.446394, -0.53406, 0.776897, -0.700858, -0.802179, -0.616515, 0.718677, 0.303042, -0.080606, -0.850593, -0.795971, 0.860487, -0.90685, 0.89858, 0.617251, 0.334305, -0.351137, -0.642574, 0.108974, -0.993964, 0.051085, -0.372012, 0.843766, 0.088025, -0.598662, 0.789035, -0.971233, -0.917609, 0.10035, -0.993908, 0.001303, 0.151006, -0.222302, -0.462642, 0.318882, 0.910461, -0.951606, -0.628088, 0.858834, 0.18648, 0.005839, -0.976863, -0.602595, -0.907466, 0.537085, 0.254335, -0.624879, -0.26462, -0.597274, 0.717515],
+        shape: [3, 5, 2, 2]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.806777, -0.564841, -0.481331, 0.559626, 0.0, 0.0, 0.0, 0.0, 0.274958, -0.659222, -0.178541, 0.689453, 0.0, 0.0, 0.0, 0.0, -0.028873, 0.053859, -0.446394, -0.53406, 0.0, 0.0, 0.0, 0.0, 0.776897, -0.700858, -0.802179, -0.616515, 0.0, 0.0, 0.0, 0.0, 0.718677, 0.303042, -0.080606, -0.850593, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.795971, 0.860487, -0.90685, 0.89858, 0.0, 0.0, 0.0, 0.0, 0.617251, 0.334305, -0.351137, -0.642574, 0.0, 0.0, 0.0, 0.0, 0.108974, -0.993964, 0.051085, -0.372012, 0.0, 0.0, 0.0, 0.0, 0.843766, 0.088025, -0.598662, 0.789035, 0.0, 0.0, 0.0, 0.0, -0.971233, -0.917609, 0.10035, -0.993908, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.001303, 0.151006, -0.222302, -0.462642, 0.0, 0.0, 0.0, 0.0, 0.318882, 0.910461, -0.951606, -0.628088, 0.0, 0.0, 0.0, 0.0, 0.858833, 0.18648, 0.005839, -0.976863, 0.0, 0.0, 0.0, 0.0, -0.602595, -0.907466, 0.537085, 0.254335, 0.0, 0.0, 0.0, 0.0, -0.624879, -0.26462, -0.597274, 0.717515, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [5, 7, 4, 2]
+      }
+    },
+    'convolutional.ZeroPadding3D.1': {
+      input: {
+        data: [0.601872, -0.028379, 0.654213, 0.217731, -0.864161, 0.422013, 0.888312, -0.714141, -0.184753, 0.224845, -0.221123, -0.847943, -0.511334, -0.871723, -0.597589, -0.889034, -0.544887, -0.004798, 0.406639, -0.35285, 0.648562, 0.325102, -0.691014, -0.77342, -0.290393, -0.724779, 0.282119, 0.149588, 0.189558, -0.216989, -0.959622, -0.6309, -0.935622, -0.799247, -0.434939, -0.46504, -0.354178, 0.299364, -0.141294, 0.7451, 0.479026, -0.401207, -0.100649, 0.210378, 0.274347, 0.18857, -0.806871, -0.319347, -0.340714, 0.158351, -0.628744, -0.831363, -0.438345, 0.476498, 0.078437, 0.440929, -0.104442, -0.298102, -0.71911, -0.639047],
+        shape: [3, 5, 2, 2]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.601872, -0.028379, 0.0, 0.0, 0.654213, 0.217731, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.864161, 0.422013, 0.0, 0.0, 0.888312, -0.714141, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.184753, 0.224845, 0.0, 0.0, -0.221123, -0.847943, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.511334, -0.871723, 0.0, 0.0, -0.597589, -0.889034, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.544887, -0.004798, 0.0, 0.0, 0.406639, -0.35285, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.648562, 0.325102, 0.0, 0.0, -0.691014, -0.77342, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.290393, -0.724779, 0.0, 0.0, 0.282119, 0.149588, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.189558, -0.216989, 0.0, 0.0, -0.959622, -0.6309, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.935622, -0.799247, 0.0, 0.0, -0.434939, -0.46504, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.354178, 0.299364, 0.0, 0.0, -0.141294, 0.7451, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.479026, -0.401207, 0.0, 0.0, -0.100649, 0.210378, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.274347, 0.18857, 0.0, 0.0, -0.806871, -0.319347, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.340714, 0.158351, 0.0, 0.0, -0.628744, -0.831363, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.438345, 0.476498, 0.0, 0.0, 0.078437, 0.440929, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.104442, -0.298102, 0.0, 0.0, -0.71911, -0.639047, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [3, 7, 4, 4]
+      }
+    },
+    'convolutional.ZeroPadding3D.2': {
+      input: {
+        data: [-0.215694, 0.441215, 0.116911, 0.53299, 0.883562, -0.535525, -0.869764, -0.596287, 0.576428, -0.689083, -0.132924, -0.129935, -0.17672, -0.29097, 0.590914, 0.992098, 0.908965, -0.170202, 0.640203, 0.178644, 0.866749, -0.545566, -0.827072, 0.420342],
+        shape: [3, 2, 1, 4]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.215694, 0.441215, 0.116911, 0.53299, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.883562, -0.535525, -0.869764, -0.596287, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.576428, -0.689083, -0.132924, -0.129935, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.17672, -0.29097, 0.590914, 0.992098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.908965, -0.170202, 0.640203, 0.178644, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.866749, -0.545566, -0.827072, 0.420342, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [9, 6, 5, 4]
+      }
+    },
+    'convolutional.ZeroPadding3D.3': {
+      input: {
+        data: [-0.215694, 0.441215, 0.116911, 0.53299, 0.883562, -0.535525, -0.869764, -0.596287, 0.576428, -0.689083, -0.132924, -0.129935, -0.17672, -0.29097, 0.590914, 0.992098, 0.908965, -0.170202, 0.640203, 0.178644, 0.866749, -0.545566, -0.827072, 0.420342],
+        shape: [3, 2, 1, 4]
+      },
+      expected: {
+        data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.215694, 0.441215, 0.116911, 0.53299, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.883562, -0.535525, -0.869764, -0.596287, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.576428, -0.689083, -0.132924, -0.129935, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.17672, -0.29097, 0.590914, 0.992098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.908965, -0.170202, 0.640203, 0.178644, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.866749, -0.545566, -0.827072, 0.420342, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        shape: [3, 8, 5, 8]
+      }
+    }
+  }
+
+  window.TEST_DATA = Object.assign({}, window.TEST_DATA, DATA)
+})()