X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=cnn-svrt.py;h=694f035edde45339823fef4e1671ec241e0a00e2;hp=bbce4c92e6426d48d15676372822ff86962066ed;hb=abbbb61852f54e90df6ac5b5f4dcb71d06f88f49;hpb=6c83bf23d43bdbf2a8cae2df4654b26d46d53046 diff --git a/cnn-svrt.py b/cnn-svrt.py index bbce4c9..694f035 100755 --- a/cnn-svrt.py +++ b/cnn-svrt.py @@ -27,6 +27,8 @@ import math from colorama import Fore, Back, Style +# Pytorch + import torch from torch import optim @@ -36,7 +38,9 @@ from torch import nn from torch.nn import functional as fn from torchvision import datasets, transforms, utils -import svrt +# SVRT + +from vignette_set import VignetteSet, CompressedVignetteSet ###################################################################### @@ -67,7 +71,7 @@ parser.add_argument('--log_file', parser.add_argument('--compress_vignettes', action='store_true', default = False, - help = 'Should we use lossless compression of vignette to reduce the memory footprint') + help = 'Use lossless compression to reduce the memory footprint') args = parser.parse_args() @@ -85,73 +89,6 @@ def log_string(s): ###################################################################### -class VignetteSet: - def __init__(self, problem_number, nb_batches): - self.batch_size = args.batch_size - self.problem_number = problem_number - self.nb_batches = nb_batches - self.nb_samples = self.nb_batches * self.batch_size - self.targets = [] - self.inputs = [] - - acc = 0.0 - acc_sq = 0.0 - - for k in range(0, self.nb_batches): - target = torch.LongTensor(self.batch_size).bernoulli_(0.5) - input = svrt.generate_vignettes(problem_number, target) - input = input.float().view(input.size(0), 1, input.size(1), input.size(2)) - if torch.cuda.is_available(): - input = input.cuda() - target = target.cuda() - acc += input.float().sum() / input.numel() - acc_sq += input.float().pow(2).sum() / input.numel() - self.targets.append(target) - self.inputs.append(input) - - mean = acc / self.nb_batches - std = math.sqrt(acc_sq / self.nb_batches - mean * mean) - for k in range(0, self.nb_batches): - self.inputs[k].sub_(mean).div_(std) - - def get_batch(self, b): - return self.inputs[b], self.targets[b] - -class CompressedVignetteSet: - def __init__(self, problem_number, nb_batches): - self.batch_size = args.batch_size - self.problem_number = problem_number - self.nb_batches = nb_batches - self.nb_samples = self.nb_batches * self.batch_size - self.targets = [] - self.input_storages = [] - - acc = 0.0 - acc_sq = 0.0 - for k in range(0, self.nb_batches): - target = torch.LongTensor(self.batch_size).bernoulli_(0.5) - input = svrt.generate_vignettes(problem_number, target) - acc += input.float().sum() / input.numel() - acc_sq += input.float().pow(2).sum() / input.numel() - self.targets.append(target) - self.input_storages.append(svrt.compress(input.storage())) - - self.mean = acc / self.nb_batches - self.std = math.sqrt(acc_sq / self.nb_batches - self.mean * self.mean) - - def get_batch(self, b): - input = torch.ByteTensor(svrt.uncompress(self.input_storages[b])).float() - input = input.view(self.batch_size, 1, 128, 128).sub_(self.mean).div_(self.std) - target = self.targets[b] - - if torch.cuda.is_available(): - input = input.cuda() - target = target.cuda() - - return input, target - -###################################################################### - # Afroze's ShallowNet # map size nb. maps @@ -174,6 +111,7 @@ class AfrozeShallowNet(nn.Module): self.conv3 = nn.Conv2d(16, 120, kernel_size=18) self.fc1 = nn.Linear(120, 84) self.fc2 = nn.Linear(84, 2) + self.name = 'shallownet' def forward(self, x): x = fn.relu(fn.max_pool2d(self.conv1(x), kernel_size=2)) @@ -184,6 +122,8 @@ class AfrozeShallowNet(nn.Module): x = self.fc2(x) return x +###################################################################### + def train_model(model, train_set): batch_size = args.batch_size criterion = nn.CrossEntropyLoss() @@ -193,7 +133,7 @@ def train_model(model, train_set): 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_set.nb_batches): input, target = train_set.get_batch(b) @@ -203,7 +143,7 @@ def train_model(model, train_set): 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 @@ -227,51 +167,75 @@ def nb_errors(model, data_set): for arg in vars(args): log_string('argument ' + str(arg) + ' ' + str(getattr(args, arg))) +###################################################################### + for problem_number in range(1, 24): - if args.compress_vignettes: - train_set = CompressedVignetteSet(problem_number, args.nb_train_batches) - test_set = CompressedVignetteSet(problem_number, args.nb_test_batches) - else: - train_set = VignetteSet(problem_number, args.nb_train_batches) - test_set = VignetteSet(problem_number, args.nb_test_batches) model = AfrozeShallowNet() if torch.cuda.is_available(): model.cuda() + model_filename = model.name + '_' + \ + str(problem_number) + '_' + \ + str(args.nb_train_batches) + '.param' + nb_parameters = 0 - for p in model.parameters(): - nb_parameters += p.numel() + for p in model.parameters(): nb_parameters += p.numel() log_string('nb_parameters {:d}'.format(nb_parameters)) - model_filename = 'model_' + str(problem_number) + '.param' - + need_to_train = False try: model.load_state_dict(torch.load(model_filename)) log_string('loaded_model ' + model_filename) except: - log_string('training_model') + 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()) + 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()) + + log_string('data_generation {:0.2f} samples / s'.format( + (train_set.nb_samples + test_set.nb_samples) / (time.time() - t)) + ) + 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_set) + nb_train_errors = nb_errors(model, train_set) - log_string('train_error {:d} {:.02f}% {:d} {:d}'.format( - problem_number, - 100 * nb_train_errors / train_set.nb_samples, - nb_train_errors, - train_set.nb_samples) - ) + log_string('train_error {:d} {:.02f}% {:d} {:d}'.format( + problem_number, + 100 * nb_train_errors / train_set.nb_samples, + nb_train_errors, + train_set.nb_samples) + ) - nb_test_errors = nb_errors(model, test_set) + nb_test_errors = nb_errors(model, test_set) - log_string('test_error {:d} {:.02f}% {:d} {:d}'.format( - problem_number, - 100 * nb_test_errors / test_set.nb_samples, - nb_test_errors, - test_set.nb_samples) - ) + log_string('test_error {:d} {:.02f}% {:d} {:d}'.format( + problem_number, + 100 * nb_test_errors / test_set.nb_samples, + nb_test_errors, + test_set.nb_samples) + ) ######################################################################