def __init__(self):
super(DeepNet2, self).__init__()
self.conv1 = nn.Conv2d( 1, 32, kernel_size=7, stride=4, padding=3)
+ self.conv2 = nn.Conv2d( 32, 256, kernel_size=5, padding=2)
+ self.conv3 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
+ self.conv4 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
+ self.conv5 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
+ self.fc1 = nn.Linear(4096, 512)
+ self.fc2 = nn.Linear(512, 512)
+ self.fc3 = nn.Linear(512, 2)
+
+ def forward(self, x):
+ x = self.conv1(x)
+ x = fn.max_pool2d(x, kernel_size=2)
+ x = fn.relu(x)
+
+ x = self.conv2(x)
+ x = fn.max_pool2d(x, kernel_size=2)
+ x = fn.relu(x)
+
+ x = self.conv3(x)
+ x = fn.relu(x)
+
+ x = self.conv4(x)
+ x = fn.relu(x)
+
+ x = self.conv5(x)
+ x = fn.max_pool2d(x, kernel_size=2)
+ x = fn.relu(x)
+
+ x = x.view(-1, 4096)
+
+ x = self.fc1(x)
+ x = fn.relu(x)
+
+ x = self.fc2(x)
+ x = fn.relu(x)
+
+ x = self.fc3(x)
+
+ return x
+
+######################################################################
+
+class DeepNet3(nn.Module):
+ name = 'deepnet3'
+
+ def __init__(self):
+ super(DeepNet3, self).__init__()
+ self.conv1 = nn.Conv2d( 1, 32, kernel_size=7, stride=4, padding=3)
self.conv2 = nn.Conv2d( 32, 128, kernel_size=5, padding=2)
self.conv3 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
self.conv4 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
self.conv5 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
- self.fc1 = nn.Linear(2048, 512)
- self.fc2 = nn.Linear(512, 512)
+ self.conv6 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
+ self.conv7 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
+ self.fc1 = nn.Linear(2048, 256)
+ self.fc2 = nn.Linear(256, 256)
self.fc3 = nn.Linear(256, 2)
def forward(self, x):
x = fn.max_pool2d(x, kernel_size=2)
x = fn.relu(x)
+ x = self.conv6(x)
+ x = fn.relu(x)
+
+ x = self.conv7(x)
+ x = fn.relu(x)
+
x = x.view(-1, 2048)
x = self.fc1(x)
######################################################################
-def train_model(model, train_set, validation_set):
+def train_model(model, model_filename, train_set, validation_set, nb_epochs_done = 0):
batch_size = args.batch_size
criterion = nn.CrossEntropyLoss()
start_t = time.time()
- for e in range(0, args.nb_epochs):
+ for e in range(nb_epochs_done, args.nb_epochs):
acc_loss = 0.0
for b in range(0, train_set.nb_batches):
input, target = train_set.get_batch(b)
log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss),
' [ETA ' + time.ctime(time.time() + dt * (args.nb_epochs - e)) + ']')
+ torch.save([ model.state_dict(), e + 1 ], model_filename)
+
if validation_set is not None:
nb_validation_errors = nb_errors(model, validation_set)
########################################
model_class = None
-for m in [ AfrozeShallowNet, AfrozeDeepNet, DeepNet2 ]:
+for m in [ AfrozeShallowNet, AfrozeDeepNet, DeepNet2, DeepNet3 ]:
if args.model == m.name:
model_class = m
break
model_filename = model.name + '_pb:' + \
str(problem_number) + '_ns:' + \
- int_to_suffix(args.nb_train_samples) + '.param'
+ int_to_suffix(args.nb_train_samples) + '.state'
nb_parameters = 0
for p in model.parameters(): nb_parameters += p.numel()
##################################################
# Tries to load the model
- need_to_train = False
try:
- model.load_state_dict(torch.load(model_filename))
+ model_state_dict, nb_epochs_done = torch.load(model_filename)
+ model.load_state_dict(model_state_dict)
log_string('loaded_model ' + model_filename)
except:
- need_to_train = True
+ nb_epochs_done = 0
+
##################################################
# Train if necessary
- if need_to_train:
+ if nb_epochs_done < args.nb_epochs:
log_string('training_model ' + model_filename)
else:
validation_set = None
- train_model(model, train_set, validation_set)
- torch.save(model.state_dict(), model_filename)
+ train_model(model, model_filename, train_set, validation_set, nb_epochs_done = nb_epochs_done)
log_string('saved_model ' + model_filename)
nb_train_errors = nb_errors(model, train_set)
##################################################
# Test if necessary
- if need_to_train or args.test_loaded_models:
+ if nb_epochs_done < args.nb_epochs or args.test_loaded_models:
t = time.time()