[test_loss, test_acc, test_prediction])
gradient_fn = theano.function([input_var, target_var], gradient)
# The training loop
print("Starting training...")
num_epochs = 20
for epoch in range(num_epochs):
# In each epoch, we do a full pass over the training data:
train_err = 0
train_batches = 0
start_time = time.time()
for batch in mini_batch.iterate_minibatches(X_train,
y_train,
500,
shuffle=True):
inputs, targets = batch
train_err += train_fn(inputs, targets)
train_batches += 1
# And a full pass over the validation data:
val_err = 0
val_acc = 0
val_batches = 0
for batch in mini_batch.iterate_minibatches(X_val,
y_val,
500,
shuffle=False):
view_fn = theano.function([input_var], test_reconstruct)
# The training loop
print("Starting training...")
num_epochs = 20
for epoch in range(num_epochs):
# In each epoch, we do a full pass over the training data:
train_err = 0
train_batches = 0
start_time = time.time()
for batch in mini_batch.iterate_minibatches(flower_train,
100,
shuffle=True):
inputs = batch
train_err += train_fn(inputs)
train_batches += 1
# Then we print the results for this epoch:
print("Epoch {} of {} took {:.3f}s".format(epoch + 1, num_epochs,
time.time() - start_time))
print(" training loss:\t\t{:.6f}".format(train_err / train_batches))
#print(" validation loss:\t\t{:.6f}".format(val_err / val_batches))
################### View reconstruction###########