X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=cc3d35f6a4e92a776021114e5c8000f077b420bd;hb=6efb16f367d497093b06bbad686f0dd7e5fa9ae3;hp=592f98217654511d776bf1bfe3ca572b7652785e;hpb=1c9bd2174185daa35eab4e71fbfe399bd9dec46a;p=pysvrt.git diff --git a/cnn-svrt.py b/cnn-svrt.py index 592f982..cc3d35f 100755 --- a/cnn-svrt.py +++ b/cnn-svrt.py @@ -49,12 +49,12 @@ parser = argparse.ArgumentParser( formatter_class = argparse.ArgumentDefaultsHelpFormatter ) -parser.add_argument('--nb_train_batches', - type = int, default = 1000, +parser.add_argument('--nb_train_samples', + type = int, default = 100000, help = 'How many samples for train') -parser.add_argument('--nb_test_batches', - type = int, default = 100, +parser.add_argument('--nb_test_samples', + type = int, default = 10000, help = 'How many samples for test') parser.add_argument('--nb_epochs', @@ -66,16 +66,20 @@ parser.add_argument('--batch_size', help = 'Mini-batch size') parser.add_argument('--log_file', - type = str, default = 'cnn-svrt.log', + type = str, default = 'default.log', help = 'Log file name') parser.add_argument('--compress_vignettes', action='store_true', default = False, help = 'Use lossless compression to reduce the memory footprint') +parser.add_argument('--deep_model', + action='store_true', default = False, + 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 error of models we load') + help = 'Should we compute the test errors of loaded models') args = parser.parse_args() @@ -86,19 +90,24 @@ pred_log_t = None print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL) -def log_string(s): +# 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 - s = Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s + + s = Fore.BLUE + '[' + time.ctime() + '] ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s log_file.write(s + '\n') log_file.flush() - print(s) + print(s + Fore.CYAN + remark + Style.RESET_ALL) ###################################################################### @@ -137,6 +146,70 @@ 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() @@ -158,9 +231,9 @@ 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) - print(Fore.CYAN + 'ETA ' + time.ctime(time.time() + dt * (args.nb_epochs - e)) + Style.RESET_ALL) + log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss), + ' [ETA ' + time.ctime(time.time() + dt * (args.nb_epochs - e)) + ']') return model @@ -186,18 +259,35 @@ 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): log_string('**** problem ' + str(problem_number) + ' ****') - model = AfrozeShallowNet() + 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() @@ -218,14 +308,16 @@ for problem_number in range(1, 24): if args.compress_vignettes: train_set = CompressedVignetteSet(problem_number, - args.nb_train_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()) + 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))) + 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) @@ -246,14 +338,16 @@ for problem_number in range(1, 24): if args.compress_vignettes: test_set = CompressedVignetteSet(problem_number, - args.nb_test_batches, args.batch_size, - cuda=torch.cuda.is_available()) + args.nb_test_samples, args.batch_size, + cuda = torch.cuda.is_available()) else: test_set = VignetteSet(problem_number, - args.nb_test_batches, args.batch_size, - cuda=torch.cuda.is_available()) + 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))) + log_string('data_generation {:0.2f} samples / s'.format( + test_set.nb_samples / (time.time() - t)) + ) nb_test_errors = nb_errors(model, test_set)