From 4b05ef4d7c171998a13b4de82b743a1b9ee0329b Mon Sep 17 00:00:00 2001
From: Leon Chen <leon@md.ai>
Date: Thu, 25 Aug 2016 21:47:18 -0400
Subject: [PATCH] update convolution tests

---
 index.html                          | 21 ++++----
 test/convolutional/convolutional.js | 79 ++++++++++++++++++++++-------
 2 files changed, 72 insertions(+), 28 deletions(-)

diff --git a/index.html b/index.html
index 4d24b05..8a30eb0 100644
--- a/index.html
+++ b/index.html
@@ -16,18 +16,19 @@
   <script src="/dist/keras.js"></script>
 
   <script>mocha.setup('bdd')</script>
+  <script src="/test/globals.js"></script>
 
-  <script src="/test/utils/globals.js"></script>
+  <script src="/test/activations/data_activations.js"></script>
+  <script src="/test/activations/activations.js"></script>
 
-  <script src="/test/data/activations.js"></script>
-  <script src="/test/data/advanced_activations.js"></script>
-  <script src="/test/data/core.js"></script>
-  <script src="/test/data/convolutional.js"></script>
-  
-  <script src="/test/activations.js"></script>
-  <script src="/test/advanced_activations.js"></script>
-  <script src="/test/core.js"></script>
-  <script src="/test/convolutional.js"></script>
+  <script src="/test/advanced_activations/data_advanced_activations.js"></script>
+  <script src="/test/advanced_activations/advanced_activations.js"></script>
+
+  <script src="/test/core/data_core.js"></script>
+  <script src="/test/core/core.js"></script>
+
+  <script src="/test/convolutional/data_convolutional.js"></script>
+  <script src="/test/convolutional/convolutional.js"></script>
 
   <script>
     // mocha.checkLeaks();
diff --git a/test/convolutional/convolutional.js b/test/convolutional/convolutional.js
index 9030c5e..3cf88c9 100644
--- a/test/convolutional/convolutional.js
+++ b/test/convolutional/convolutional.js
@@ -21,24 +21,67 @@ describe('Layers: Convolutional', function () {
       console.log('\n%cConvolution2D', styles.h2)
     })
 
-    it('[convolutional.Convolution2D.0] [CPU] should produce expected values for activation=linear, borderMode=valid, subsample=[1,1], dimOrdering=tf, biase=true', function () {
-      const key = 'convolutional.Convolution2D.0'
-      const [nbRow, nbCol, nbFilter] = TEST_DATA[key].expected.shape
-      const attrs = { activation: 'linear', borderMode: 'valid', subsample: [1, 1], dimOrdering: 'tf', bias: true }
-      console.log(`\n%c[${key}] [CPU] test 1: ${nbFilter} ${nbRow}x${nbCol} filters on 5x5x2 input, activation='${attrs.activation}', border_mode='${attrs.borderMode}', subsample=${attrs.subsample}, dim_ordering='${attrs.dimOrdering}', bias=${attrs.bias}`, styles.h3)
-      let testLayer = new layers.Convolution2D(nbFilter, nbRow, nbCol, attrs)
-      testLayer.setWeights(TEST_DATA[key].weights.map(w => new KerasJS.Tensor(w.data, w.shape)))
-      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))
+    const testParams = [
+      {
+        mode: 'CPU',
+        inputShape: [5, 5, 2],
+        kernelShape: [4, 3, 3],
+        attrs: { activation: 'linear', borderMode: 'valid', subsample: [1, 1], dimOrdering: 'tf', bias: true }
+      },
+      {
+        mode: 'CPU',
+        inputShape: [5, 5, 2],
+        kernelShape: [4, 3, 3],
+        attrs: { activation: 'linear', borderMode: 'valid', subsample: [1, 1], dimOrdering: 'tf', bias: false }
+      },
+      {
+        mode: 'CPU',
+        inputShape: [5, 5, 2],
+        kernelShape: [4, 3, 3],
+        attrs: { activation: 'relu', borderMode: 'valid', subsample: [2, 2], dimOrdering: 'tf', bias: true }
+      },
+      {
+        mode: 'CPU',
+        inputShape: [7, 7, 3],
+        kernelShape: [5, 4, 4],
+        attrs: { activation: 'relu', borderMode: 'valid', subsample: [2, 1], dimOrdering: 'tf', bias: true }
+      },
+      {
+        mode: 'CPU',
+        inputShape: [5, 5, 2],
+        kernelShape: [4, 3, 3],
+        attrs: { activation: 'relu', borderMode: 'same', subsample: [1, 1], dimOrdering: 'tf', bias: true }
+      },
+      {
+        mode: 'CPU',
+        inputShape: [4, 4, 2],
+        kernelShape: [4, 3, 3],
+        attrs: { activation: 'relu', borderMode: 'same', subsample: [2, 2], dimOrdering: 'tf', bias: true }
+      }
+    ]
+
+    testParams.forEach(({ mode, inputShape, kernelShape, attrs }, i) => {
+      const key = `convolutional.Convolution2D.${i}`
+      const [inputRows, inputCols, inputChannels] = inputShape
+      const [nbFilter, nbRow, nbCol] = kernelShape
+      const title = `[${key}] [CPU] test 1: ${nbFilter} ${nbRow}x${nbCol} filters on ${inputRows}x${inputCols}x${inputChannels} input, activation='${attrs.activation}', border_mode='${attrs.borderMode}', subsample=${attrs.subsample}, dim_ordering='${attrs.dimOrdering}', bias=${attrs.bias}`
+
+      it(title, function () {
+        console.log(`\n%c${title}`, styles.h3)
+        let testLayer = new layers.Convolution2D(nbFilter, nbRow, nbCol, attrs)
+        testLayer.setWeights(TEST_DATA[key].weights.map(w => new KerasJS.Tensor(w.data, w.shape)))
+        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))
+      })
     })
   })
 })