s.run(classes,
{input_X: X_train_flat})) # this is slow and usually skipped
valid_accuracy = accuracy_score(y_val, s.run(classes,
{input_X: X_val_flat}))
simpleTrainingCurves.add(train_loss, val_loss, train_accuracy,
valid_accuracy)
# # Submit a linear model
# In[35]:
## GRADED PART, DO NOT CHANGE!
# Testing shapes
grader.set_answer(
"9XaAS",
grading_utils.get_tensors_shapes_string(
[W, b, input_X, input_y, logits, probas, classes]))
# Validation loss
grader.set_answer("vmogZ", s.run(loss, {
input_X: X_val_flat,
input_y: y_val_oh
}))
# Validation accuracy
grader.set_answer("RMv95",
accuracy_score(y_val, s.run(classes, {input_X: X_val_flat})))
# In[36]:
# you can make submission with answers so far to check yourself at this stage
grader.submit(COURSERA_EMAIL, COURSERA_TOKEN)
# # MLP with hidden layers
batch_losses = []
for batch_start in range(0, X_train_flat.shape[0], BATCH_SIZE): # data is already shuffled
_, batch_loss = s.run([step, loss], {input_X: X_train_flat[batch_start:batch_start+BATCH_SIZE],
input_y: y_train_oh[batch_start:batch_start+BATCH_SIZE]})
# collect batch losses, this is almost free as we need a forward pass for backprop anyway
batch_losses.append(batch_loss)
train_loss = np.mean(batch_losses)
val_loss = s.run(loss, {input_X: X_val_flat, input_y: y_val_oh}) # this part is usually small
train_accuracy = accuracy_score(y_train, s.run(classes, {input_X: X_train_flat})) # this is slow and usually skipped
valid_accuracy = accuracy_score(y_val, s.run(classes, {input_X: X_val_flat}))
simpleTrainingCurves.add(train_loss, val_loss, train_accuracy, valid_accuracy)
## GRADED PART, DO NOT CHANGE!
# Testing shapes
grader.set_answer("9XaAS", grading_utils.get_tensors_shapes_string([W, b, input_X, input_y, logits, probas, classes]))
# Validation loss
grader.set_answer("vmogZ", s.run(loss, {input_X: X_val_flat, input_y: y_val_oh}))
# Validation accuracy
grader.set_answer("RMv95", accuracy_score(y_val, s.run(classes, {input_X: X_val_flat})))
# you can make submission with answers so far to check yourself at this stage
grader.submit(COURSERA_EMAIL, COURSERA_TOKEN)
# write the code here to get a new `step` operation and then run the cell with training loop above.
# name your variables in the same way (e.g. logits, probas, classes, etc) for safety.
### YOUR CODE HERE ###
hidden1 = tf.layers.dense(input_X, 256, activation=tf.nn.sigmoid)
hidden2 = tf.layers.dense(hidden1, 256, activation=tf.nn.sigmoid)
logits = tf.layers.dense(hidden2, 10)
