- if torch.cuda.is_available():
- train_input, train_target = train_input.cuda(), train_target.cuda()
- test_input, test_target = test_input.cuda(), test_target.cuda()
+ log_string('############### problem ' + str(problem_number) + ' ###############')
+
+ if args.deep_model:
+ model = AfrozeDeepNet()
+ else:
+ model = AfrozeShallowNet()
+
+ if torch.cuda.is_available(): model.cuda()
+
+ model_filename = model.name + '_pb:' + \
+ str(problem_number) + '_ns:' + \
+ int_to_suffix(args.nb_train_samples) + '.param'
+
+ nb_parameters = 0
+ for p in model.parameters(): nb_parameters += p.numel()
+ log_string('nb_parameters {:d}'.format(nb_parameters))
+
+ ##################################################
+ # Tries to load the model
+
+ need_to_train = False
+ try:
+ model.load_state_dict(torch.load(model_filename))
+ log_string('loaded_model ' + model_filename)
+ except:
+ need_to_train = True
+
+ ##################################################
+ # Train if necessary
+
+ if need_to_train:
+
+ log_string('training_model ' + model_filename)
+
+ t = time.time()
+
+ train_set = VignetteSet(problem_number,
+ args.nb_train_samples, args.batch_size,
+ cuda = torch.cuda.is_available())
+
+ log_string('data_generation {:0.2f} samples / s'.format(
+ train_set.nb_samples / (time.time() - t))
+ )
+
+ train_model(model, train_set)
+ torch.save(model.state_dict(), model_filename)
+ log_string('saved_model ' + model_filename)
+
+ nb_train_errors = nb_errors(model, train_set)
+
+ log_string('train_error {:d} {:.02f}% {:d} {:d}'.format(
+ problem_number,
+ 100 * nb_train_errors / train_set.nb_samples,
+ nb_train_errors,
+ train_set.nb_samples)
+ )
+
+ ##################################################
+ # Test if necessary