X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=cnn-svrt.py;h=5dc91c82e66e99322ee77ec95e6e8c4b337dcdff;hp=7bef242de186a1bbcbad4a84444c5c3311a9445e;hb=15f2d2cf0a655234cfa435789e26238b95f5a371;hpb=08ef6b7c332153cd72b7a225e27ee7af8882f313 diff --git a/cnn-svrt.py b/cnn-svrt.py index 7bef242..5dc91c8 100755 --- a/cnn-svrt.py +++ b/cnn-svrt.py @@ -45,47 +45,64 @@ from vignette_set import VignetteSet, CompressedVignetteSet ###################################################################### parser = argparse.ArgumentParser( - description = 'Simple convnet test on the SVRT.', + description = "Convolutional networks for the SVRT. Written by Francois Fleuret, (C) Idiap research institute.", formatter_class = argparse.ArgumentDefaultsHelpFormatter ) -parser.add_argument('--nb_train_batches', - type = int, default = 1000, - help = 'How many samples for train') +parser.add_argument('--nb_train_samples', + type = int, default = 100000) -parser.add_argument('--nb_test_batches', - type = int, default = 100, - help = 'How many samples for test') +parser.add_argument('--nb_test_samples', + type = int, default = 10000) parser.add_argument('--nb_epochs', - type = int, default = 50, - help = 'How many training epochs') + type = int, default = 50) parser.add_argument('--batch_size', - type = int, default = 100, - help = 'Mini-batch size') + type = int, default = 100) parser.add_argument('--log_file', - type = str, default = 'cnn-svrt.log', - help = 'Log file name') + type = str, default = 'default.log') parser.add_argument('--compress_vignettes', - action='store_true', default = False, + action='store_true', default = True, help = 'Use lossless compression to reduce the memory footprint') +parser.add_argument('--deep_model', + action='store_true', default = True, + help = 'Use Afroze\'s Alexnet-like deep model') + +parser.add_argument('--test_loaded_models', + action='store_true', default = False, + help = 'Should we compute the test errors of loaded models') + args = parser.parse_args() ###################################################################### log_file = open(args.log_file, 'w') +pred_log_t = None print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL) -def log_string(s): - s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + s - log_file.write(s + '\n') +# Log and prints the string, with a time stamp. Does not log the +# remark +def log_string(s, remark = ''): + global pred_log_t + + t = time.time() + + if pred_log_t is None: + elapsed = 'start' + else: + elapsed = '+{:.02f}s'.format(t - pred_log_t) + + pred_log_t = t + + log_file.write('[' + time.ctime() + '] ' + elapsed + ' ' + s + '\n') log_file.flush() - print(s) + + print(Fore.BLUE + '[' + time.ctime() + '] ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s + Fore.CYAN + remark + Style.RESET_ALL) ###################################################################### @@ -124,6 +141,70 @@ class AfrozeShallowNet(nn.Module): ###################################################################### +# Afroze's DeepNet + +# map size nb. maps +# ---------------------- +# input 128x128 1 +# -- conv(21x21 x 32 stride=4) -> 28x28 32 +# -- max(2x2) -> 14x14 6 +# -- conv(7x7 x 96) -> 8x8 16 +# -- max(2x2) -> 4x4 16 +# -- conv(5x5 x 96) -> 26x36 16 +# -- conv(3x3 x 128) -> 36x36 16 +# -- conv(3x3 x 128) -> 36x36 16 + +# -- conv(5x5 x 120) -> 1x1 120 +# -- reshape -> 120 1 +# -- full(3x84) -> 84 1 +# -- full(84x2) -> 2 1 + +class AfrozeDeepNet(nn.Module): + def __init__(self): + super(AfrozeDeepNet, self).__init__() + self.conv1 = nn.Conv2d( 1, 32, kernel_size=7, stride=4, padding=3) + self.conv2 = nn.Conv2d( 32, 96, kernel_size=5, padding=2) + self.conv3 = nn.Conv2d( 96, 128, kernel_size=3, padding=1) + self.conv4 = nn.Conv2d(128, 128, kernel_size=3, padding=1) + self.conv5 = nn.Conv2d(128, 96, kernel_size=3, padding=1) + self.fc1 = nn.Linear(1536, 256) + self.fc2 = nn.Linear(256, 256) + self.fc3 = nn.Linear(256, 2) + self.name = 'deepnet' + + 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, 1536) + + x = self.fc1(x) + x = fn.relu(x) + + x = self.fc2(x) + x = fn.relu(x) + + x = self.fc3(x) + + return x + +###################################################################### + def train_model(model, train_set): batch_size = args.batch_size criterion = nn.CrossEntropyLoss() @@ -133,6 +214,8 @@ def train_model(model, train_set): optimizer = optim.SGD(model.parameters(), lr = 1e-2) + start_t = time.time() + for e in range(0, args.nb_epochs): acc_loss = 0.0 for b in range(0, train_set.nb_batches): @@ -143,7 +226,9 @@ def train_model(model, train_set): model.zero_grad() loss.backward() optimizer.step() - log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss)) + dt = (time.time() - start_t) / (e + 1) + log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss), + ' [ETA ' + time.ctime(time.time() + dt * (args.nb_epochs - e)) + ']') return model @@ -169,44 +254,65 @@ for arg in vars(args): ###################################################################### +def int_to_suffix(n): + if n > 1000000 and n%1000000 == 0: + return str(n//1000000) + 'M' + elif n > 1000 and n%1000 == 0: + return str(n//1000) + 'K' + else: + return str(n) + +###################################################################### + +if args.nb_train_samples%args.batch_size > 0 or args.nb_test_samples%args.batch_size > 0: + print('The number of samples must be a multiple of the batch size.') + raise + for problem_number in range(1, 24): - model = AfrozeShallowNet() + 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 + '_' + \ str(problem_number) + '_' + \ - str(args.nb_train_batches) + '.param' + 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)) + need_to_train = False try: - model.load_state_dict(torch.load(model_filename)) log_string('loaded_model ' + model_filename) - except: + need_to_train = True + + if need_to_train: log_string('training_model ' + model_filename) + t = time.time() + if args.compress_vignettes: train_set = CompressedVignetteSet(problem_number, - args.nb_train_batches, args.batch_size, - cuda=torch.cuda.is_available()) - test_set = CompressedVignetteSet(problem_number, - args.nb_test_batches, args.batch_size, - cuda=torch.cuda.is_available()) + args.nb_train_samples, args.batch_size, + cuda = torch.cuda.is_available()) else: train_set = VignetteSet(problem_number, - args.nb_train_batches, args.batch_size, - cuda=torch.cuda.is_available()) - test_set = VignetteSet(problem_number, - args.nb_test_batches, args.batch_size, - cuda=torch.cuda.is_available()) + 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) @@ -221,6 +327,23 @@ for problem_number in range(1, 24): train_set.nb_samples) ) + if need_to_train or args.test_loaded_models: + + t = time.time() + + if args.compress_vignettes: + test_set = CompressedVignetteSet(problem_number, + args.nb_test_samples, args.batch_size, + cuda = torch.cuda.is_available()) + else: + test_set = VignetteSet(problem_number, + args.nb_test_samples, args.batch_size, + cuda = torch.cuda.is_available()) + + log_string('data_generation {:0.2f} samples / s'.format( + test_set.nb_samples / (time.time() - t)) + ) + nb_test_errors = nb_errors(model, test_set) log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(