Added failing test for convolutional1D with input (16,1)

notebooks/convolutional/Convolution1D.ipynb

@@ -270,6 +270,61 @@
     "print('out:', format_decimal(result[0].ravel().tolist()))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2016-11-07T13:56:00.927837",
+     "start_time": "2016-11-07T13:56:00.641182"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "W shape: (3, 1, 1, 3)\n",
+      "W: [0.895265, -0.546905, 0.18884, -0.143383, 0.528281, -0.994279, -0.285153, 0.81939, -0.087838]\n",
+      "b shape: (3,)\n",
+      "b: [0.895265, -0.546905, 0.18884]\n",
+      "\n",
+      "in shape: (16, 1)\n",
+      "in: [-0.143383, 0.528281, -0.994279, -0.285153, 0.81939, -0.087838, 0.963605, 0.734714, 0.972055, 0.846533, -0.392613, 0.692207, -0.757556, 0.571153, -0.49899, -0.807941]\n",
+      "out shape: (16, 3)\n",
+      "out: [0.765182, -0.189783, 0.284999, 0.974674, -1.004109, -0.27616, 1.59209, -1.594735, 1.302239, -0.187643, 0.51763, 0.212628, 0.547538, -0.030059, -0.671994, 1.366655, -0.251868, 0.346268, 0.468956, 0.612206, -0.850375, 1.375417, 0.110722, -0.445086, 1.172261, 0.258435, -0.713268, 1.756087, -0.953023, -0.4348, 1.512045, -0.650102, 0.678265, 0.66054, -0.587236, -0.507005, 1.460728, -0.857683, 1.02261, 0.277446, -0.239732, -0.478271, 1.70853, -1.784897, 0.8638, 0.564381, -0.700825, 0.897929]\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_in_shape = (16, 1)\n",
+    "conv = Convolution1D(3, 3, activation='linear', border_mode='same', subsample_length=1, bias=True)\n",
+    "\n",
+    "layer_0 = Input(shape=data_in_shape)\n",
+    "layer_1 = conv(layer_0)\n",
+    "model = Model(input=layer_0, output=layer_1)\n",
+    "\n",
+    "# set weights to random (use seed for reproducibility)\n",
+    "weights = []\n",
+    "for w in model.get_weights():\n",
+    "    np.random.seed(200)\n",
+    "    weights.append(2 * np.random.random(w.shape) - 1)\n",
+    "model.set_weights(weights)\n",
+    "print('W shape:', weights[0].shape)\n",
+    "print('W:', format_decimal(weights[0].ravel().tolist()))\n",
+    "print('b shape:', weights[1].shape)\n",
+    "print('b:', format_decimal(weights[1].ravel().tolist()))\n",
+    "\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,
@@ -279,6 +334,9 @@
    "outputs": [],
    "source": []
   }
+
+
+
  ],
  "metadata": {
   "kernelspec": {

test/convolutional/Convolution1D.js

@@ -28,7 +28,12 @@ describe('convolutional layer: Convolution1D', function () {
       inputShape: [8, 3],
       kernelShape: [2, 7],
       attrs: { activation: 'tanh', borderMode: 'same', subsampleLength: 1, bias: true }
-    }
+    },
+    {
+        inputShape: [16, 1],
+        kernelShape: [3, 3],
+        attrs: { activation: 'linear', borderMode: 'same', subsampleLength: 1, bias: true }
+    },
   ]
 
   before(function () {

test/convolutional/data_Convolution1D.js

@@ -83,7 +83,27 @@
         data: [0.854959, 0.355561, 0.888899, -0.9834, -0.825345, 0.941694, -0.490434, -0.699848, 0.872523, -0.887886, -0.408331, -0.018902, 0.959544, 0.66633, -0.779488, 0.038157],
         shape: [8, 2]
       }
-    }
+  },
+      'convolutional.Convolution1D.3': {
+        input: {
+          data: [-0.143383, 0.528281, -0.994279, -0.285153, 0.81939, -0.087838, 0.963605, 0.734714, 0.972055, 0.846533, -0.392613, 0.692207, -0.757556, 0.571153, -0.49899, -0.807941],
+          shape: [16, 1]
+        },
+        weights: [
+          {
+            data: [0.895265, -0.546905, 0.18884, -0.143383, 0.528281, -0.994279, -0.285153, 0.81939, -0.087838],
+            shape: [3, 1, 1, 3]
+          },
+          {
+            data: [0.895265, -0.546905, 0.18884],
+            shape: [3]
+          }
+        ],
+        expected: {
+          data: [0.765182, -0.189783, 0.284999, 0.974674, -1.004109, -0.27616, 1.59209, -1.594735, 1.302239, -0.187643, 0.51763, 0.212628, 0.547538, -0.030059, -0.671994, 1.366655, -0.251868, 0.346268, 0.468956, 0.612206, -0.850375, 1.375417, 0.110722, -0.445086, 1.172261, 0.258435, -0.713268, 1.756087, -0.953023, -0.4348, 1.512045, -0.650102, 0.678265, 0.66054, -0.587236, -0.507005, 1.460728, -0.857683, 1.02261, 0.277446, -0.239732, -0.478271, 1.70853, -1.784897, 0.8638, 0.564381, -0.700825, 0.897929],
+          shape: [16, 3]
+        }
+      }
   }
 
   window.TEST_DATA = Object.assign({}, window.TEST_DATA, DATA)