Add files via upload

Author: YJango

MNIST with shape info TFrecord.ipynb

@@ -374,13 +374,13 @@
     }
    ],
    "source": [
-    "#padding_info = ({'image':[28,28,1],'label':[],'image_shape':[None]})\n",
-    "test_input_fn = input_fn_maker('mnist_tfrecord/test/',  'mnist_tfrecord/data_info.csv',batch_size = 4,\n",
-    "                               padding = None)\n",
-    "train_input_fn = input_fn_maker('mnist_tfrecord/train/',  'mnist_tfrecord/data_info.csv', shuffle=True, batch_size = 512,\n",
-    "                               padding = None)\n",
-    "train_eval_fn = input_fn_maker('mnist_tfrecord/train/',  'mnist_tfrecord/data_info.csv', batch_size = 512,\n",
-    "                               padding = None)\n",
+    "padding_info = ({'image':[None,None,1],'label':[],'image_shape':[None]})\n",
+    "test_input_fn = input_fn_maker('mnist_tfrecord/test/',  'mnist_tfrecord/data_info.csv',batch_size = 1,\n",
+    "                               padding = padding_info)\n",
+    "train_input_fn = input_fn_maker('mnist_tfrecord/train/',  'mnist_tfrecord/data_info.csv', shuffle=True, batch_size = 1,\n",
+    "                               padding = padding_info)\n",
+    "train_eval_fn = input_fn_maker('mnist_tfrecord/train/',  'mnist_tfrecord/data_info.csv', batch_size = 1,\n",
+    "                               padding = padding_info)\n",
     "test_inputs = test_input_fn()"
    ]
   },
@@ -395,13 +395,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "shape of image: (4, 28, 28, 1)\n",
-      "value of label: [7 2 1 0]\n",
+      "shape of image: (1, 28, 28, 1)\n",
+      "value of label: [7]\n",
       "value of 'image_shape':\n",
-      " [[28 28  1]\n",
-      " [14 56  1]\n",
-      " [28 28  1]\n",
-      " [14 56  1]]\n"
+      " [[28 28  1]]\n"
      ]
     }
    ],
@@ -422,17 +419,8 @@
     "sess =tf.InteractiveSession()\n",
     "# Because test_inputs contain n_batch examples, and each example has different image shape.\n",
     "# executing tf.reshape once can not do the work.\n",
-    "# the first 4 examples in the batch\n",
-    "reshaped_image_example1 = tf.reshape(test_inputs['image'][0],test_inputs['image_shape'][0])\n",
-    "reshaped_image_example2 = tf.reshape(test_inputs['image'][1],test_inputs['image_shape'][1])\n",
-    "reshaped_image_example3 = tf.reshape(test_inputs['image'][2],test_inputs['image_shape'][2])\n",
-    "reshaped_image_example4 = tf.reshape(test_inputs['image'][3],test_inputs['image_shape'][3])\n",
-    "\n",
-    "list_image_examples = [reshaped_image_example1,reshaped_image_example2,reshaped_image_example3,reshaped_image_example4]\n",
-    "\n",
-    "# following code does the same thing\n",
-    "batch_size = 4\n",
-    "list_image_examples = [tf.reshape(test_inputs['image'][i],test_inputs['image_shape'][i]) for i in np.arange(batch_size)]"
+    "batch_size = 1\n",
+    "list_image_examples = tf.reshape(test_inputs['image'][0],test_inputs['image_shape'][0])"
    ]
   },
   {
@@ -444,29 +432,60 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "image shape of example 0: (28, 28, 1)\n",
-      "image shape of example 1: (14, 56, 1)\n",
-      "image shape of example 2: (28, 28, 1)\n",
-      "image shape of example 3: (14, 56, 1)\n"
+      "image shape of example (28, 28, 1)\n"
      ]
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x7fcfbaaebdd8>"
+       "<matplotlib.figure.Figure at 0x7f9cdd03bf28>"
       ]
      },
      "metadata": {},
      "output_type": "display_data"
     }
    ],
    "source": [
-    "example1,example2,example3,example4= sess.run(list_image_examples)\n",
-    "for i,e in enumerate([example1,example2,example3,example4]):\n",
-    "    plt.subplot(1,4,i+1)\n",
-    "    plt.imshow(e.reshape((28,28)),cmap=plt.cm.gray)\n",
-    "    print('image shape of example %s:' %i, e.shape)"
+    "example= sess.run(list_image_examples)\n",
+    "plt.imshow(example.reshape((28,28)),cmap=plt.cm.gray)\n",
+    "print('image shape of example', example.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "conv = tf.layers.conv2d(\n",
+    "        inputs=test_inputs['image'],\n",
+    "        filters=64,\n",
+    "        kernel_size=[5, 5],\n",
+    "        padding=\"same\",\n",
+    "        activation=tf.nn.relu,\n",
+    "        name = 'conv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(1, 14, 56, 64)"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tf.global_variables_initializer().run()\n",
+    "sess.run(conv).shape"
    ]
   }
  ],