X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=ab1b363a2b9dac04b28d02f975197008fe71fad6;hb=7a46506f936bad2e136424b68cbd92890d46830c;hp=1d5e887c832f59cbb9d56317f3413ba4d24dbe03;hpb=3f3a2df9cb54730206a94a294d60d48422333a11;p=pysvrt.git diff --git a/cnn-svrt.py b/cnn-svrt.py index 1d5e887..ab1b363 100755 --- a/cnn-svrt.py +++ b/cnn-svrt.py @@ -23,6 +23,7 @@ import time import argparse + from colorama import Fore, Back, Style import torch @@ -43,18 +44,22 @@ parser = argparse.ArgumentParser( formatter_class = argparse.ArgumentDefaultsHelpFormatter ) -parser.add_argument('--nb_train_samples', - type = int, default = 100000, +parser.add_argument('--nb_train_batches', + type = int, default = 1000, help = 'How many samples for train') -parser.add_argument('--nb_test_samples', - type = int, default = 10000, +parser.add_argument('--nb_test_batches', + type = int, default = 100, help = 'How many samples for test') parser.add_argument('--nb_epochs', - type = int, default = 25, + type = int, default = 50, help = 'How many training epochs') +parser.add_argument('--batch_size', + type = int, default = 100, + help = 'Mini-batch size') + parser.add_argument('--log_file', type = str, default = 'cnn-svrt.log', help = 'Log file name') @@ -68,8 +73,7 @@ log_file = open(args.log_file, 'w') print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL) def log_string(s): - s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + \ - str(problem_number) + ' ' + s + s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + s log_file.write(s + '\n') log_file.flush() print(s) @@ -81,7 +85,7 @@ def generate_set(p, n): t = time.time() input = svrt.generate_vignettes(p, target) t = time.time() - t - log_string('DATA_SET_GENERATION {:.02f} sample/s'.format(n / t)) + log_string('data_set_generation {:.02f} sample/s'.format(n / t)) input = input.view(input.size(0), 1, input.size(1), input.size(2)).float() return Variable(input), Variable(target) @@ -89,21 +93,21 @@ def generate_set(p, n): # Afroze's ShallowNet -# map size nb. maps -# ---------------------- -# 128x128 1 -# -- conv(21x21) -> 108x108 6 -# -- max(2x2) -> 54x54 6 -# -- conv(19x19) -> 36x36 16 -# -- max(2x2) -> 18x18 16 -# -- conv(18x18) -> 1x1 120 -# -- reshape -> 120 1 -# -- full(120x84) -> 84 1 -# -- full(84x2) -> 2 1 - -class Net(nn.Module): +# map size nb. maps +# ---------------------- +# input 128x128 1 +# -- conv(21x21 x 6) -> 108x108 6 +# -- max(2x2) -> 54x54 6 +# -- conv(19x19 x 16) -> 36x36 16 +# -- max(2x2) -> 18x18 16 +# -- conv(18x18 x 120) -> 1x1 120 +# -- reshape -> 120 1 +# -- full(120x84) -> 84 1 +# -- full(84x2) -> 2 1 + +class AfrozeShallowNet(nn.Module): def __init__(self): - super(Net, self).__init__() + super(AfrozeShallowNet, self).__init__() self.conv1 = nn.Conv2d(1, 6, kernel_size=21) self.conv2 = nn.Conv2d(6, 16, kernel_size=19) self.conv3 = nn.Conv2d(16, 120, kernel_size=18) @@ -119,14 +123,14 @@ class Net(nn.Module): x = self.fc2(x) return x -def train_model(train_input, train_target): - model, criterion = Net(), nn.CrossEntropyLoss() +def train_model(model, train_input, train_target): + bs = args.batch_size + criterion = nn.CrossEntropyLoss() if torch.cuda.is_available(): - model.cuda() criterion.cuda() - optimizer, bs = optim.SGD(model.parameters(), lr = 1e-2), 100 + optimizer = optim.SGD(model.parameters(), lr = 1e-2) for k in range(0, args.nb_epochs): acc_loss = 0.0 @@ -137,15 +141,16 @@ def train_model(train_input, train_target): model.zero_grad() loss.backward() optimizer.step() - log_string('TRAIN_LOSS {:d} {:f}'.format(k, acc_loss)) + log_string('train_loss {:d} {:f}'.format(k, acc_loss)) return model ###################################################################### -def nb_errors(model, data_input, data_target, bs = 100): - ne = 0 +def nb_errors(model, data_input, data_target): + bs = args.batch_size + ne = 0 for b in range(0, data_input.size(0), bs): output = model.forward(data_input.narrow(0, b, bs)) wta_prediction = output.data.max(1)[1].view(-1) @@ -158,23 +163,45 @@ def nb_errors(model, data_input, data_target, bs = 100): ###################################################################### +for arg in vars(args): + log_string('argument ' + str(arg) + ' ' + str(getattr(args, arg))) + for problem_number in range(1, 24): - train_input, train_target = generate_set(problem_number, args.nb_train_samples) - test_input, test_target = generate_set(problem_number, args.nb_test_samples) + train_input, train_target = generate_set(problem_number, + args.nb_train_batches * args.batch_size) + test_input, test_target = generate_set(problem_number, + args.nb_test_batches * args.batch_size) + model = AfrozeShallowNet() 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() + model.cuda() mu, std = train_input.data.mean(), train_input.data.std() train_input.data.sub_(mu).div_(std) test_input.data.sub_(mu).div_(std) - model = train_model(train_input, train_target) + nb_parameters = 0 + for p in model.parameters(): + nb_parameters += p.numel() + log_string('nb_parameters {:d}'.format(nb_parameters)) + + model_filename = 'model_' + str(problem_number) + '.param' + + try: + model.load_state_dict(torch.load(model_filename)) + log_string('loaded_model ' + model_filename) + except: + log_string('training_model') + train_model(model, train_input, train_target) + torch.save(model.state_dict(), model_filename) + log_string('saved_model ' + model_filename) nb_train_errors = nb_errors(model, train_input, train_target) - log_string('TRAIN_ERROR {:.02f}% {:d} {:d}'.format( + log_string('train_error {:d} {:.02f}% {:d} {:d}'.format( + problem_number, 100 * nb_train_errors / train_input.size(0), nb_train_errors, train_input.size(0)) @@ -182,7 +209,8 @@ for problem_number in range(1, 24): nb_test_errors = nb_errors(model, test_input, test_target) - log_string('TEST_ERROR {:.02f}% {:d} {:d}'.format( + log_string('test_error {:d} {:.02f}% {:d} {:d}'.format( + problem_number, 100 * nb_test_errors / test_input.size(0), nb_test_errors, test_input.size(0))