finished alterations to lab 2

Author: Shorna Alam

lab2/Part1_MNIST.ipynb

@@ -61,12 +61,13 @@
       },
       "outputs": [],
       "source": [
-        "# Import Tensorflow 2.0\n",
+        "#Import Comet\n",
         "%pip install comet_ml\n",
         "import comet_ml\n",
         "comet_ml.init(project_name=\"6.s191lab2.1.1\")\n",
         "comet_model_1 = comet_ml.Experiment()\n",
         "\n",
+        "# Import Tensorflow 2.0\n",
         "%tensorflow_version 2.x\n",
         "import tensorflow as tf \n",
         "\n",
@@ -276,7 +277,8 @@
         "BATCH_SIZE = 64\n",
         "EPOCHS = 5\n",
         "\n",
-        "model.fit(train_images, train_labels, batch_size=BATCH_SIZE, epochs=EPOCHS)"
+        "model.fit(train_images, train_labels, batch_size=BATCH_SIZE, epochs=EPOCHS)\n",
+        "comet_model_1.end()"
       ]
     },
     {
@@ -419,6 +421,9 @@
       },
       "outputs": [],
       "source": [
+        "comet_ml.init(project_name=\"6.s191lab2.1.2\")\n",
+        "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='''TODO''', loss='''TODO''', metrics=['accuracy']) # TODO"
       ]
@@ -441,7 +446,8 @@
       "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('''TODO''')"
+        "cnn_model.fit('''TODO''')\n",
+        "comet_model_2.end() "
       ]
     },
     {
@@ -652,6 +658,9 @@
         "plotter = mdl.util.PeriodicPlotter(sec=2, xlabel='Iterations', ylabel='Loss', scale='semilogy')\n",
         "optimizer = tf.keras.optimizers.SGD(learning_rate=1e-2) # define our optimizer\n",
         "\n",
+        "comet_ml.init(project_name=\"6.s191lab2.1.3\")\n",
+        "comet_model_3 = comet_ml.Experiment()\n",
+        "\n",
         "if hasattr(tqdm, '_instances'): tqdm._instances.clear() # clear if it exists\n",
         "\n",
         "for idx in tqdm(range(0, train_images.shape[0], batch_size)):\n",
@@ -666,6 +675,7 @@
         "\n",
         "    #'''TODO: compute the categorical cross entropy loss\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",
         "\n",
         "  loss_history.append(loss_value.numpy().mean()) # append the loss to the loss_history record\n",
         "  plotter.plot(loss_history.get())\n",
@@ -674,7 +684,9 @@
         "  '''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 = # TODO\n",
-        "  optimizer.apply_gradients(zip(grads, cnn_model.trainable_variables))\n"
+        "  optimizer.apply_gradients(zip(grads, cnn_model.trainable_variables))\n",
+        "\n",
+        "comet_model_3.end()\n"
       ]
     },
     {

lab2/Part2_FaceDetection.ipynb

@@ -75,6 +75,12 @@
       },
       "outputs": [],
       "source": [
+        "# Import Comet\n",
+        "!pip install comet_ml\n",
+        "import comet_ml\n",
+        "comet_ml.init(project_name=\"6.s191lab2.2.1\")\n",
+        "comet_model_1 = comet_ml.Experiment()\n",
+        "\n",
         "# Import Tensorflow 2.0\n",
         "%tensorflow_version 2.x\n",
         "import tensorflow as tf\n",
@@ -300,9 +306,11 @@
         "    x, y = loader.get_batch(batch_size)\n",
         "    loss = standard_train_step(x, y)\n",
         "\n",
+        "    comet_model_1.log_metric(\"loss\", loss.numpy().mean(), idx)\n",
         "    # Record the loss and plot the evolution of the loss as a function of training\n",
         "    loss_history.append(loss.numpy().mean())\n",
-        "    plotter.plot(loss_history.get())"
+        "    plotter.plot(loss_history.get())\n",
+        "comet_model_1.end()"
       ]
     },
     {
@@ -756,6 +764,9 @@
       "source": [
         "### Training the SS-VAE ###\n",
         "\n",
+        "comet_ml.init(project_name=\"6.s191lab2.2.2\")\n",
+        "comet_model_2 = comet_ml.Experiment()\n",
+        "\n",
         "# Hyperparameters\n",
         "batch_size = 32\n",
         "learning_rate = 5e-4\n",
@@ -806,10 +817,13 @@
         "    (x, y) = loader.get_batch(batch_size)\n",
         "    # loss optimization\n",
         "    loss = ss_vae_train_step(x, y)\n",
+        "    comet_model_2.log_metric(\"loss\", loss, step=j)\n",
         "    \n",
         "    # plot the progress every 200 steps\n",
         "    if j % 500 == 0: \n",
-        "      mdl.util.plot_sample(x, y, ss_vae)"
+        "      mdl.util.plot_sample(x, y, ss_vae)\n",
+        "  \n",
+        "comet_model_2.end()"
       ]
     },
     {