tf l2p2 student version

Author: avaamini

lab2/TF_Part1_MNIST.ipynb

@@ -10,9 +10,9 @@
         "  <td align=\"center\"><a target=\"_blank\" href=\"http://introtodeeplearning.com\">\n",
         "        <img src=\"https://i.ibb.co/Jr88sn2/mit.png\" style=\"padding-bottom:5px;\" />\n",
         "      Visit MIT Deep Learning</a></td>\n",
-        "  <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab2/solutions/TF_Part1_MNIST_Solution.ipynb\">\n",
+        "  <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab2/TF_Part1_MNIST.ipynb\">\n",
         "        <img src=\"https://i.ibb.co/2P3SLwK/colab.png\"  style=\"padding-bottom:5px;\" />Run in Google Colab</a></td>\n",
-        "  <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/master/lab2/solutions/TF_Part1_MNIST_Solution.ipynb\">\n",
+        "  <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/master/lab2/TF_Part1_MNIST.ipynb\">\n",
         "        <img src=\"https://i.ibb.co/xfJbPmL/github.png\"  height=\"70px\" style=\"padding-bottom:5px;\"  />View Source on GitHub</a></td>\n",
         "</table>\n",
         "\n",
@@ -216,12 +216,10 @@
         "      tf.keras.layers.Flatten(),\n",
         "\n",
         "      # '''TODO: Define the activation function for the first fully connected (Dense) layer.'''\n",
-        "      tf.keras.layers.Dense(128, activation=tf.nn.relu),\n",
-        "      # tf.keras.layers.Dense(128, activation= '''TODO'''),\n",
+        "      tf.keras.layers.Dense(128, activation= '''TODO'''),\n",
         "\n",
         "      # '''TODO: Define the second Dense layer to output the classification probabilities'''\n",
-        "      tf.keras.layers.Dense(10, activation=tf.nn.softmax)\n",
-        "      # [TODO Dense layer to output classification probabilities]\n",
+        "      '''[TODO Dense layer to output classification probabilities]'''\n",
         "\n",
         "  ])\n",
         "  return fc_model\n",
@@ -348,8 +346,7 @@
       "outputs": [],
       "source": [
         "'''TODO: Use the evaluate method to test the model!'''\n",
-        "test_loss, test_acc = model.evaluate(test_images, test_labels) # TODO\n",
-        "# test_loss, test_acc = # TODO\n",
+        "test_loss, test_acc = # TODO\n",
         "\n",
         "print('Test accuracy:', test_acc)"
       ]
@@ -410,29 +407,24 @@
         "    cnn_model = tf.keras.Sequential([\n",
         "\n",
         "        # TODO: Define the first convolutional layer\n",
-        "        tf.keras.layers.Conv2D(filters=24, kernel_size=(3,3), activation=tf.nn.relu),\n",
-        "        # tf.keras.layers.Conv2D('''TODO''')\n",
+        "        tf.keras.layers.Conv2D('''TODO''')\n",
         "\n",
         "        # TODO: Define the first max pooling layer\n",
-        "        tf.keras.layers.MaxPool2D(pool_size=(2,2)),\n",
-        "        # tf.keras.layers.MaxPool2D('''TODO''')\n",
+        "        tf.keras.layers.MaxPool2D('''TODO''')\n",
         "\n",
         "        # TODO: Define the second convolutional layer\n",
-        "        tf.keras.layers.Conv2D(filters=36, kernel_size=(3,3), activation=tf.nn.relu),\n",
-        "        # tf.keras.layers.Conv2D('''TODO''')\n",
+        "        tf.keras.layers.Conv2D('''TODO''')\n",
         "\n",
         "        # TODO: Define the second max pooling layer\n",
-        "        tf.keras.layers.MaxPool2D(pool_size=(2,2)),\n",
-        "        # tf.keras.layers.MaxPool2D('''TODO''')\n",
+        "        tf.keras.layers.MaxPool2D('''TODO''')\n",
         "\n",
         "        tf.keras.layers.Flatten(),\n",
         "        tf.keras.layers.Dense(128, activation=tf.nn.relu),\n",
         "\n",
         "        # TODO: Define the last Dense layer to output the classification\n",
         "        # probabilities. Pay attention to the activation needed a probability\n",
         "        # output\n",
-        "        tf.keras.layers.Dense(10, activation=tf.nn.softmax)\n",
-        "        # [TODO Dense layer to output classification probabilities]\n",
+        "        '''[TODO Dense layer to output classification probabilities]'''\n",
         "    ])\n",
         "\n",
         "    return cnn_model\n",
@@ -467,10 +459,7 @@
         "comet_model_2 = comet_ml.Experiment()\n",
         "\n",
         "'''TODO: Define the compile operation with your optimizer and learning rate of choice'''\n",
-        "cnn_model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-3),\n",
-        "              loss='sparse_categorical_crossentropy',\n",
-        "              metrics=['accuracy'])\n",
-        "# cnn_model.compile(optimizer='''TODO''', loss='''TODO''', metrics=['accuracy']) # TODO"
+        "cnn_model.compile(optimizer='''TODO''', loss='''TODO''', metrics=['accuracy']) # TODO"
       ]
     },
     {
@@ -491,8 +480,7 @@
       "outputs": [],
       "source": [
         "'''TODO: Use model.fit to train the CNN model, with the same batch_size and number of epochs previously used.'''\n",
-        "cnn_model.fit(train_images, train_labels, batch_size=BATCH_SIZE, epochs=EPOCHS)\n",
-        "# cnn_model.fit('''TODO''')\n",
+        "cnn_model.fit('''TODO''')\n",
         "# comet_model_2.end()"
       ]
     },
@@ -514,8 +502,7 @@
       "outputs": [],
       "source": [
         "'''TODO: Use the evaluate method to test the model!'''\n",
-        "test_loss, test_acc = cnn_model.evaluate(test_images, test_labels)\n",
-        "# test_loss, test_acc = # TODO\n",
+        "test_loss, test_acc = # TODO\n",
         "\n",
         "print('Test accuracy:', test_acc)"
       ]
@@ -594,8 +581,7 @@
       "source": [
         "'''TODO: identify the digit with the highest confidence prediction for the first\n",
         "    image in the test dataset. '''\n",
-        "prediction = np.argmax(predictions[0])\n",
-        "# prediction = # TODO\n",
+        "prediction = # TODO\n",
         "\n",
         "print(prediction)"
       ]
@@ -725,22 +711,19 @@
         "  # GradientTape to record differentiation operations\n",
         "  with tf.GradientTape() as tape:\n",
         "    #'''TODO: feed the images into the model and obtain the predictions'''\n",
-        "    logits = cnn_model(images)\n",
-        "    # logits = # TODO\n",
+        "    logits = # TODO\n",
         "\n",
         "    #'''TODO: compute the categorical cross entropy loss\n",
-        "    loss_value = tf.keras.backend.sparse_categorical_crossentropy(labels, logits)\n",
+        "    loss_value = tf.keras.backend.sparse_categorical_crossentropy('''TODO''', '''TODO''') # TODO\n",
         "    comet_model_3.log_metric(\"loss\", loss_value.numpy().mean(), step=idx)\n",
-        "    # loss_value = tf.keras.backend.sparse_categorical_crossentropy('''TODO''', '''TODO''') # TODO\n",
         "\n",
         "  loss_history.append(loss_value.numpy().mean()) # append the loss to the loss_history record\n",
         "  plotter.plot(loss_history.get())\n",
         "\n",
         "  # Backpropagation\n",
         "  '''TODO: Use the tape to compute the gradient against all parameters in the CNN model.\n",
         "      Use cnn_model.trainable_variables to access these parameters.'''\n",
-        "  grads = tape.gradient(loss_value, cnn_model.trainable_variables)\n",
-        "  # grads = # TODO\n",
+        "  grads = # TODO\n",
         "  optimizer.apply_gradients(zip(grads, cnn_model.trainable_variables))\n",
         "\n",
         "comet_model_3.log_figure(figure=plt)\n",
@@ -786,4 +769,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}