# define optimizer operation to minimize the loss
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_step = optimizer.minimize(decoder.loss)
# will be used to save/load network weights.
# you need to reset your default graph and define it in the same way to be able to load the saved weights!
saver = tf.train.Saver()
# intialize all variables
s.run(tf.global_variables_initializer())
## GRADED PART, DO NOT CHANGE!
# Decoder shapes test
grader.set_answer(
"rbpnH",
grading_utils.test_decoder_shapes(decoder, IMG_EMBED_SIZE, vocab, s))
# Decoder random loss test
grader.set_answer(
"E2OIL",
grading_utils.test_random_decoder_loss(decoder, IMG_EMBED_SIZE, vocab, s))
# you can make submission with answers so far to check yourself at this stage
grader.submit(COURSERA_EMAIL, COURSERA_TOKEN)
"""## Training loop
Evaluate train and validation metrics through training and log them. Ensure that loss decreases.
"""
train_captions_indexed = np.array(train_captions_indexed)
val_captions_indexed = np.array(val_captions_indexed)
loss = tf.reduce_sum(tf.multiply(xent, flat_loss_mask)) / tf.reduce_sum(flat_loss_mask)
# define optimizer operation to minimize the loss
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_step = optimizer.minimize(decoder.loss)
# will be used to save/load network weights.
# you need to reset your default graph and define it in the same way to be able to load the saved weights!
saver = tf.train.Saver()
# intialize all variables
s.run(tf.global_variables_initializer())
## GRADED PART, DO NOT CHANGE!
# Decoder shapes test
grader.set_answer("rbpnH", grading_utils.test_decoder_shapes(decoder, IMG_EMBED_SIZE, vocab, s))
# Decoder random loss test
grader.set_answer("E2OIL", grading_utils.test_random_decoder_loss(decoder, IMG_EMBED_SIZE, vocab, s))
# you can make submission with answers so far to check yourself at this stage
grader.submit(COURSERA_EMAIL, COURSERA_TOKEN)
"""## Training loop
Evaluate train and validation metrics through training and log them. Ensure that loss decreases.
"""
train_captions_indexed = np.array(train_captions_indexed)
val_captions_indexed = np.array(val_captions_indexed)
# generate batch via random sampling of images and captions for them,
# we use `max_len` parameter to control the length of the captions (truncating long captions)