making todos face detection

Author: avaamini

lab2/Part2_FaceDetection.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/2023/lab2/Part2_FaceDetection.ipynb\">\n",
+        "  <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/2023/lab2/solutions/Part2_FaceDetection_Solution.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/2023/lab2/Part2_FaceDetection.ipynb\">\n",
+        "  <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/2023/lab2/solutions/Part2_FaceDetection_Solution.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",
@@ -435,22 +435,19 @@
         "def vae_loss_function(x, x_recon, mu, logsigma, kl_weight=0.0005):\n",
         "  # TODO: Define the latent loss. Note this is given in the equation for L_{KL}\n",
         "  # in the text block directly above\n",
-        "  latent_loss = 0.5 * tf.reduce_sum(tf.exp(logsigma) + tf.square(mu) - 1.0 - logsigma, axis=1)\n",
-        "  # latent_loss = # TODO\n",
+        "  latent_loss = # TODO\n",
         "\n",
         "  # TODO: Define the reconstruction loss as the mean absolute pixel-wise \n",
         "  # difference between the input and reconstruction. Hint: you'll need to \n",
         "  # use tf.reduce_mean, and supply an axis argument which specifies which \n",
         "  # dimensions to reduce over. For example, reconstruction loss needs to average \n",
         "  # over the height, width, and channel image dimensions.\n",
         "  # https://www.tensorflow.org/api_docs/python/tf/math/reduce_mean\n",
-        "  reconstruction_loss = tf.reduce_mean(tf.abs(x-x_recon), axis=(1,2,3))\n",
-        "  # reconstruction_loss = # TODO\n",
+        "  reconstruction_loss = # TODO\n",
         "\n",
         "  # TODO: Define the VAE loss. Note this is given in the equation for L_{VAE}\n",
         "  # in the text block directly above\n",
-        "  vae_loss = kl_weight * latent_loss + reconstruction_loss\n",
-        "  # vae_loss = # TODO\n",
+        "  vae_loss = # TODO\n",
         "  \n",
         "  return vae_loss"
       ]
@@ -495,8 +492,8 @@
         "\n",
         "  # TODO: Define the reparameterization computation!\n",
         "  # Note the equation is given in the text block immediately above.\n",
-        "  z = z_mean + tf.math.exp(0.5 * z_logsigma) * epsilon\n",
-        "  # z = # TODO\n",
+        "  z = # TODO\n",
+        "  \n",
         "  return z"
       ]
     },
@@ -588,25 +585,19 @@
         "def ss_vae_loss_function(x, x_pred, y, y_logit, mu, logsigma):\n",
         "\n",
         "  # TODO: call the relevant function to obtain VAE loss, defined earlier in the lab\n",
-        "  vae_loss = vae_loss_function(x, x_pred, mu, logsigma)\n",
-        "  # vae_loss = vae_loss_function('''TODO''') # TODO\n",
+        "  vae_loss = vae_loss_function('''TODO''') # TODO\n",
         "\n",
         "  # TODO: define the classification loss using sigmoid_cross_entropy\n",
         "  # https://www.tensorflow.org/api_docs/python/tf/nn/sigmoid_cross_entropy_with_logits\n",
-        "  classification_loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=y, logits=y_logit)\n",
-        "  # classification_loss = # TODO\n",
+        "  classification_loss = # TODO\n",
         "\n",
         "  # Use the training data labels to create variable face_indicator:\n",
         "  #   indicator that reflects which training data are images of faces\n",
         "  face_indicator = tf.cast(tf.equal(y, 1), tf.float32)\n",
         "\n",
         "  # TODO: define the SS-VAE total loss! Use tf.reduce_mean to average over all\n",
         "  # samples\n",
-        "  total_loss = tf.reduce_mean(\n",
-        "      classification_loss + \n",
-        "      face_indicator * vae_loss\n",
-        "  )\n",
-        "  # total_loss = # TODO\n",
+        "  total_loss = # TODO\n",
         "\n",
         "  return total_loss, classification_loss, vae_loss"
       ]
@@ -708,8 +699,7 @@
         "  # Decode the latent space and output reconstruction\n",
         "  def decode(self, z):\n",
         "    # TODO: use the decoder (self.decoder) to output the reconstruction\n",
-        "    reconstruction = self.decoder(z)\n",
-        "    # reconstruction = # TODO\n",
+        "    reconstruction = # TODO\n",
         "    return reconstruction\n",
         "\n",
         "  # The call function will be used to pass inputs x through the core VAE\n",
@@ -719,12 +709,11 @@
         "\n",
         "    # TODO: call the sampling function that you created above using \n",
         "    #       z_mean and z_logsigma\n",
-        "    z = sampling(z_mean, z_logsigma)\n",
-        "    # z = # TODO\n",
+        "    z = # TODO\n",
         "\n",
         "    # TODO: reconstruction\n",
-        "    recon = self.decode(z)\n",
-        "    # recon = # TODO\n",
+        "    recon = # TODO\n",
+        "    \n",
         "    return y_logit, z_mean, z_logsigma, recon\n",
         "\n",
         "  # Predict face or not face logit for given input x\n",
@@ -789,13 +778,11 @@
         "    y_logit, z_mean, z_logsigma, x_recon = ss_vae(x)\n",
         "\n",
         "    '''TODO: call the SS_VAE loss function to compute the loss'''\n",
-        "    loss, class_loss, _ = ss_vae_loss_function(x, x_recon, y, y_logit, z_mean, z_logsigma)\n",
-        "    # loss, class_loss = ss_vae_loss_function('''TODO arguments''') # TODO\n",
+        "    loss, class_loss = ss_vae_loss_function('''TODO arguments''') # TODO\n",
         "  \n",
         "  '''TODO: use the GradientTape.gradient method to compute the gradients.\n",
         "     Hint: this is with respect to the trainable_variables of the SS_VAE.'''\n",
-        "  grads = tape.gradient(loss, ss_vae.trainable_variables)\n",
-        "  # grads = tape.gradient('''TODO''', '''TODO''') # TODO\n",
+        "  grads = tape.gradient('''TODO''', '''TODO''') # TODO\n",
         "\n",
         "  # apply gradients to variables\n",
         "  optimizer.apply_gradients(zip(grads, ss_vae.trainable_variables))\n",