X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=1511e823dfe6f71458cc7ba541e51c932efd9794;hb=838ded8648c0d870a3645ed49b2e9b86ffeb141d;hp=f3d350eb9ea9203f408a0603e7c0458b88801e95;hpb=aca8ab8e7d30f1f79829d57897238469df5468b0;p=pysvrt.git diff --git a/cnn-svrt.py b/cnn-svrt.py index f3d350e..1511e82 100755 --- a/cnn-svrt.py +++ b/cnn-svrt.py @@ -25,18 +25,22 @@ import time import argparse import math import distutils.util +import re from colorama import Fore, Back, Style # Pytorch import torch +import torchvision from torch import optim +from torch import multiprocessing from torch import FloatTensor as Tensor from torch.autograd import Variable from torch import nn from torch.nn import functional as fn + from torchvision import datasets, transforms, utils # SVRT @@ -72,13 +76,16 @@ parser.add_argument('--batch_size', parser.add_argument('--log_file', type = str, default = 'default.log') +parser.add_argument('--nb_exemplar_vignettes', + type = int, default = 32) + parser.add_argument('--compress_vignettes', type = distutils.util.strtobool, default = 'True', help = 'Use lossless compression to reduce the memory footprint') -parser.add_argument('--deep_model', - type = distutils.util.strtobool, default = 'True', - help = 'Use Afroze\'s Alexnet-like deep model') +parser.add_argument('--model', + type = str, default = 'deepnet', + help = 'What model to use') parser.add_argument('--test_loaded_models', type = distutils.util.strtobool, default = 'False', @@ -94,13 +101,15 @@ args = parser.parse_args() log_file = open(args.log_file, 'a') pred_log_t = None +last_tag_t = time.time() print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL) # Log and prints the string, with a time stamp. Does not log the # remark + def log_string(s, remark = ''): - global pred_log_t + global pred_log_t, last_tag_t t = time.time() @@ -111,10 +120,14 @@ def log_string(s, remark = ''): pred_log_t = t - log_file.write('[' + time.ctime() + '] ' + elapsed + ' ' + s + '\n') + if t > last_tag_t + 3600: + last_tag_t = t + print(Fore.RED + time.ctime() + Style.RESET_ALL) + + log_file.write(re.sub(' ', '_', time.ctime()) + ' ' + elapsed + ' ' + s + '\n') log_file.flush() - print(Fore.BLUE + '[' + time.ctime() + '] ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s + Fore.CYAN + remark + Style.RESET_ALL) + print(Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s + Fore.CYAN + remark + Style.RESET_ALL) ###################################################################### @@ -133,6 +146,8 @@ def log_string(s, remark = ''): # -- full(84x2) -> 2 1 class AfrozeShallowNet(nn.Module): + name = 'shallownet' + def __init__(self): super(AfrozeShallowNet, self).__init__() self.conv1 = nn.Conv2d(1, 6, kernel_size=21) @@ -140,7 +155,6 @@ 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)) @@ -156,6 +170,9 @@ class AfrozeShallowNet(nn.Module): # Afroze's DeepNet class AfrozeDeepNet(nn.Module): + + name = 'deepnet' + def __init__(self): super(AfrozeDeepNet, self).__init__() self.conv1 = nn.Conv2d( 1, 32, kernel_size=7, stride=4, padding=3) @@ -166,7 +183,6 @@ class AfrozeDeepNet(nn.Module): 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) @@ -201,6 +217,53 @@ class AfrozeDeepNet(nn.Module): ###################################################################### +class DeepNet2(nn.Module): + name = 'deepnet2' + + def __init__(self): + super(DeepNet2, self).__init__() + self.conv1 = nn.Conv2d( 1, 32, kernel_size=7, stride=4, padding=3) + self.conv2 = nn.Conv2d( 32, 128, kernel_size=5, padding=2) + self.conv3 = nn.Conv2d(128, 128, kernel_size=3, padding=1) + self.conv4 = nn.Conv2d(128, 128, kernel_size=3, padding=1) + self.conv5 = nn.Conv2d(128, 128, kernel_size=3, padding=1) + self.fc1 = nn.Linear(2048, 512) + self.fc2 = nn.Linear(512, 512) + self.fc3 = nn.Linear(512, 2) + + 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, 2048) + + x = self.fc1(x) + x = fn.relu(x) + + x = self.fc2(x) + x = fn.relu(x) + + x = self.fc3(x) + + return x + +###################################################################### + def nb_errors(model, data_set): ne = 0 for b in range(0, data_set.nb_batches): @@ -288,6 +351,21 @@ class vignette_logger(): ) self.last_t = t +def save_examplar_vignettes(data_set, nb, name): + n = torch.randperm(data_set.nb_samples).narrow(0, 0, nb) + + for k in range(0, nb): + b = n[k] // data_set.batch_size + m = n[k] % data_set.batch_size + i, t = data_set.get_batch(b) + i = i[m].float() + i.sub_(i.min()) + i.div_(i.max()) + if k == 0: patchwork = Tensor(nb, 1, i.size(1), i.size(2)) + patchwork[k].copy_(i) + + torchvision.utils.save_image(patchwork, name) + ###################################################################### if args.nb_train_samples%args.batch_size > 0 or args.nb_test_samples%args.batch_size > 0: @@ -303,14 +381,24 @@ else: log_string('using_uncompressed_vignettes') VignetteSet = svrtset.VignetteSet +######################################## +model_class = None +for m in [ AfrozeShallowNet, AfrozeDeepNet, DeepNet2 ]: + if args.model == m.name: + model_class = m + break +if model_class is None: + print('Unknown model ' + args.model) + raise + +log_string('using model class ' + m.name) +######################################## + for problem_number in map(int, args.problems.split(',')): log_string('############### problem ' + str(problem_number) + ' ###############') - if args.deep_model: - model = AfrozeDeepNet() - else: - model = AfrozeShallowNet() + model = model_class() if torch.cuda.is_available(): model.cuda() @@ -350,6 +438,10 @@ for problem_number in map(int, args.problems.split(',')): train_set.nb_samples / (time.time() - t)) ) + if args.nb_exemplar_vignettes > 0: + save_examplar_vignettes(train_set, args.nb_exemplar_vignettes, + 'examplar_{:d}.png'.format(problem_number)) + if args.validation_error_threshold > 0.0: validation_set = VignetteSet(problem_number, args.nb_validation_samples, args.batch_size,