import time
import argparse
import math
+
import distutils.util
import re
+import signal
from colorama import Fore, Back, Style
type = distutils.util.strtobool, default = 'True',
help = 'Use lossless compression to reduce the memory footprint')
+parser.add_argument('--save_test_mistakes',
+ type = distutils.util.strtobool, default = 'False')
+
parser.add_argument('--model',
type = str, default = 'deepnet',
help = 'What model to use')
######################################################################
log_file = open(args.log_file, 'a')
+log_file.write('\n')
+log_file.write('@@@@@@@@@@@@@@@@@@@ ' + time.ctime() + ' @@@@@@@@@@@@@@@@@@@\n')
+log_file.write('\n')
+
pred_log_t = None
last_tag_t = time.time()
log_file.write(re.sub(' ', '_', time.ctime()) + ' ' + elapsed + ' ' + s + '\n')
log_file.flush()
- print(Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s + Fore.CYAN + remark + Style.RESET_ALL)
+ print(Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed \
+ + Style.RESET_ALL
+ + ' ' \
+ + s + Fore.CYAN + remark \
+ + Style.RESET_ALL)
+
+######################################################################
+
+def handler_sigint(signum, frame):
+ log_string('got sigint')
+ exit(0)
+
+def handler_sigterm(signum, frame):
+ log_string('got sigterm')
+ exit(0)
+
+signal.signal(signal.SIGINT, handler_sigint)
+signal.signal(signal.SIGTERM, handler_sigterm)
######################################################################
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.fc3 = nn.Linear(512, 2)
+ 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 = self.conv1(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 nb_errors(model, data_set):
+def nb_errors(model, data_set, mistake_filename_pattern = None):
ne = 0
for b in range(0, data_set.nb_batches):
input, target = data_set.get_batch(b)
for i in range(0, data_set.batch_size):
if wta_prediction[i] != target[i]:
ne = ne + 1
-
+ if mistake_filename_pattern is not None:
+ img = input[i].clone()
+ img.sub_(img.min())
+ img.div_(img.max())
+ k = b * data_set.batch_size + i
+ filename = mistake_filename_pattern.format(k, target[i])
+ torchvision.utils.save_image(img, filename)
+ print(Fore.RED + 'Wrote ' + filename + Style.RESET_ALL)
return ne
######################################################################
-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)
print('The number of samples must be a multiple of the batch size.')
raise
-log_string('############### start ###############')
-
if args.compress_vignettes:
log_string('using_compressed_vignettes')
VignetteSet = svrtset.CompressedVignetteSet
########################################
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()
args.nb_test_samples, args.batch_size,
cuda = torch.cuda.is_available())
- nb_test_errors = nb_errors(model, test_set)
+ nb_test_errors = nb_errors(model, test_set,
+ mistake_filename_pattern = 'mistake_{:06d}_{:d}.png')
log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
problem_number,