for i in range(batches):
torch.cuda.synchronize(
) # synchronize function call for precise time measurement
batch_start = timer.perf_counter()
bXt = Variable(torch.from_numpy(bX).cuda())
bYt = Variable(torch.from_numpy(bY).cuda())
optimizer.zero_grad()
output = net(bXt)
loss = criterion(output, bYt.long())
loss.backward()
optimizer.step()
torch.cuda.synchronize(
) # synchronize function call for precise time measurement
batch_end = timer.perf_counter()
batch_time.append(batch_end - batch_start)
batch_loss.append(float(loss.data.cpu().numpy()))
train_end = timer.perf_counter() # end of training
# Write results
print_results(batch_time)
check_results(batch_loss, batch_time, train_start, train_end)
write_results(script_name=os.path.basename(__file__),
bench=bench,
experiment=experiment,
parameters=params,
run_time=batch_time,
version=version)
for dim in shape:
variable_parametes *= dim.value
params += variable_parametes
print('# network parameters: ' + str(params))
# Start training
with tf.Session(config=config) as sess:
sess.run(init)
time = []
for i in range(batches):
print('Batch {}/{}'.format(i, batches))
start = timer.perf_counter()
_, output = sess.run([train_step, h3],
feed_dict={
x: bX,
y: bY,
x_len: b_lenX
})
end = timer.perf_counter()
time.append(end - start)
assert (output.shape == (batch_size, classes))
# Write results
write_results(script_name=os.path.basename(__file__),
bench=bench,
experiment=experiment,
parameters=params,
run_time=time,
version=version)
print_results(time)
