X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=cnn-svrt.py;h=084606aa67b18191a969043c214e075d22825fe0;hp=3e20f8e4f5e0c4d79476cdb58dcffc2de504bf73;hb=94548cd44f585308c13511b82320a04d96a0731c;hpb=034e1a7f3e7174a2eebfcff388fa0fefc8c331e7 diff --git a/cnn-svrt.py b/cnn-svrt.py index 3e20f8e..084606a 100755 --- a/cnn-svrt.py +++ b/cnn-svrt.py @@ -23,6 +23,7 @@ import time import argparse +import math from colorama import Fore, Back, Style @@ -35,7 +36,7 @@ from torch import nn from torch.nn import functional as fn from torchvision import datasets, transforms, utils -import svrt +from vignette_set import VignetteSet, CompressedVignetteSet ###################################################################### @@ -44,22 +45,30 @@ 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 = 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') +parser.add_argument('--compress_vignettes', + action='store_true', default = False, + help = 'Use lossless compression to reduce the memory footprint') + args = parser.parse_args() ###################################################################### @@ -76,17 +85,6 @@ def log_string(s): ###################################################################### -def generate_set(p, n): - target = torch.LongTensor(n).bernoulli_(0.5) - t = time.time() - input = svrt.generate_vignettes(p, target) - t = time.time() - 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) - -###################################################################### - # Afroze's ShallowNet # map size nb. maps @@ -101,9 +99,9 @@ def generate_set(p, n): # -- full(120x84) -> 84 1 # -- full(84x2) -> 2 1 -class Net(nn.Module): +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) @@ -119,44 +117,40 @@ class Net(nn.Module): x = self.fc2(x) return x -def train_model(train_input, train_target): - model, criterion = Net(), nn.CrossEntropyLoss() - - nb_parameters = 0 - for p in model.parameters(): - nb_parameters += p.numel() - log_string('NB_PARAMETERS {:d}'.format(nb_parameters)) +def train_model(model, train_set): + batch_size = 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): + for e in range(0, args.nb_epochs): acc_loss = 0.0 - for b in range(0, train_input.size(0), bs): - output = model.forward(train_input.narrow(0, b, bs)) - loss = criterion(output, train_target.narrow(0, b, bs)) + for b in range(0, train_set.nb_batches): + input, target = train_set.get_batch(b) + output = model.forward(Variable(input)) + loss = criterion(output, Variable(target)) acc_loss = acc_loss + loss.data[0] model.zero_grad() loss.backward() optimizer.step() - log_string('TRAIN_LOSS {:d} {:f}'.format(k, acc_loss)) + log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss)) return model ###################################################################### -def nb_errors(model, data_input, data_target, bs = 100): +def nb_errors(model, data_set): ne = 0 - - for b in range(0, data_input.size(0), bs): - output = model.forward(data_input.narrow(0, b, bs)) + for b in range(0, data_set.nb_batches): + input, target = data_set.get_batch(b) + output = model.forward(Variable(input)) wta_prediction = output.data.max(1)[1].view(-1) - for i in range(0, bs): - if wta_prediction[i] != data_target.narrow(0, b, bs).data[i]: + for i in range(0, data_set.batch_size): + if wta_prediction[i] != target[i]: ne = ne + 1 return ne @@ -164,38 +158,53 @@ def nb_errors(model, data_input, data_target, bs = 100): ###################################################################### for arg in vars(args): - log_string('ARGUMENT ' + str(arg) + ' ' + str(getattr(args, arg))) + 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) + if args.compress_vignettes: + train_set = CompressedVignetteSet(problem_number, args.nb_train_batches, args.batch_size) + test_set = CompressedVignetteSet(problem_number, args.nb_test_batches, args.batch_size) + else: + train_set = VignetteSet(problem_number, args.nb_train_batches, args.batch_size) + test_set = VignetteSet(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() + + nb_parameters = 0 + for p in model.parameters(): + nb_parameters += p.numel() + log_string('nb_parameters {:d}'.format(nb_parameters)) - 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_filename = 'model_' + str(problem_number) + '.param' - model = train_model(train_input, train_target) + try: + model.load_state_dict(torch.load(model_filename)) + log_string('loaded_model ' + model_filename) + except: + log_string('training_model') + train_model(model, train_set) + torch.save(model.state_dict(), model_filename) + log_string('saved_model ' + model_filename) - nb_train_errors = nb_errors(model, train_input, train_target) + nb_train_errors = nb_errors(model, train_set) - log_string('TRAIN_ERROR {:d} {:.02f}% {:d} {:d}'.format( + log_string('train_error {:d} {:.02f}% {:d} {:d}'.format( problem_number, - 100 * nb_train_errors / train_input.size(0), + 100 * nb_train_errors / train_set.nb_samples, nb_train_errors, - train_input.size(0)) + train_set.nb_samples) ) - nb_test_errors = nb_errors(model, test_input, test_target) + nb_test_errors = nb_errors(model, test_set) - log_string('TEST_ERROR {:d} {:.02f}% {:d} {:d}'.format( + log_string('test_error {:d} {:.02f}% {:d} {:d}'.format( problem_number, - 100 * nb_test_errors / test_input.size(0), + 100 * nb_test_errors / test_set.nb_samples, nb_test_errors, - test_input.size(0)) + test_set.nb_samples) ) ######################################################################