X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=0c63b85f184470bfed0e9d8daf7bb1e395234bda;hb=24789240ca5395a857c16e602a2d0f5e8cb176d8;hp=ade87ceea78dba435a3f9982e2e55f1bb719357e;hpb=1ae0133746fd78a916ac540475c64a0e5fccd3e4;p=pysvrt.git

diff --git a/cnn-svrt.py b/cnn-svrt.py
index ade87ce..0c63b85 100755
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -29,7 +29,10 @@ import distutils.util
 import re
 import signal
 
-from colorama import Fore, Back, Style
+try:
+    from colorama import Fore, Back, Style
+except ImportError:
+    Fore, Back, Style = '', '', ''
 
 # Pytorch
 
@@ -85,6 +88,9 @@ parser.add_argument('--compress_vignettes',
                     type = distutils.util.strtobool, default = 'True',
                     help = 'Use lossless compression to reduce the memory footprint')
 
+parser.add_argument('--save_test_mistakes',
+                    type = distutils.util.strtobool, default = 'False')
+
 parser.add_argument('--model',
                     type = str, default = 'deepnet',
                     help = 'What model to use')
@@ -102,6 +108,10 @@ args = parser.parse_args()
 ######################################################################
 
 log_file = open(args.log_file, 'a')
+log_file.write('\n')
+log_file.write('@@@@@@@@@@@@@@@@@@@ ' + time.ctime() + ' @@@@@@@@@@@@@@@@@@@\n')
+log_file.write('\n')
+
 pred_log_t = None
 last_tag_t = time.time()
 
@@ -241,12 +251,13 @@ class DeepNet2(nn.Module):
 
     def __init__(self):
         super(DeepNet2, self).__init__()
+        self.nb_channels = 512
         self.conv1 = nn.Conv2d(  1,  32, kernel_size=7, stride=4, padding=3)
-        self.conv2 = nn.Conv2d( 32, 256, kernel_size=5, padding=2)
-        self.conv3 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.conv4 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.conv5 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.fc1 = nn.Linear(4096, 512)
+        self.conv2 = nn.Conv2d( 32, self.nb_channels, kernel_size=5, padding=2)
+        self.conv3 = nn.Conv2d(self.nb_channels, self.nb_channels, kernel_size=3, padding=1)
+        self.conv4 = nn.Conv2d(self.nb_channels, self.nb_channels, kernel_size=3, padding=1)
+        self.conv5 = nn.Conv2d(self.nb_channels, self.nb_channels, kernel_size=3, padding=1)
+        self.fc1 = nn.Linear(16 * self.nb_channels, 512)
         self.fc2 = nn.Linear(512, 512)
         self.fc3 = nn.Linear(512, 2)
 
@@ -269,7 +280,7 @@ class DeepNet2(nn.Module):
         x = fn.max_pool2d(x, kernel_size=2)
         x = fn.relu(x)
 
-        x = x.view(-1, 4096)
+        x = x.view(-1, 16 * self.nb_channels)
 
         x = self.fc1(x)
         x = fn.relu(x)
@@ -338,7 +349,7 @@ class DeepNet3(nn.Module):
 
 ######################################################################
 
-def nb_errors(model, data_set):
+def nb_errors(model, data_set, mistake_filename_pattern = None):
     ne = 0
     for b in range(0, data_set.nb_batches):
         input, target = data_set.get_batch(b)
@@ -348,7 +359,14 @@ def nb_errors(model, data_set):
         for i in range(0, data_set.batch_size):
             if wta_prediction[i] != target[i]:
                 ne = ne + 1
-
+                if mistake_filename_pattern is not None:
+                    img = input[i].clone()
+                    img.sub_(img.min())
+                    img.div_(img.max())
+                    k = b * data_set.batch_size + i
+                    filename = mistake_filename_pattern.format(k, target[i])
+                    torchvision.utils.save_image(img, filename)
+                    print(Fore.RED + 'Wrote ' + filename + Style.RESET_ALL)
     return ne
 
 ######################################################################
@@ -448,8 +466,6 @@ if args.nb_train_samples%args.batch_size > 0 or args.nb_test_samples%args.batch_
     print('The number of samples must be a multiple of the batch size.')
     raise
 
-log_string('############### start ###############')
-
 if args.compress_vignettes:
     log_string('using_compressed_vignettes')
     VignetteSet = svrtset.CompressedVignetteSet
@@ -527,7 +543,10 @@ for problem_number in map(int, args.problems.split(',')):
         else:
             validation_set = None
 
-        train_model(model, model_filename, train_set, validation_set, nb_epochs_done = nb_epochs_done)
+        train_model(model, model_filename,
+                    train_set, validation_set,
+                    nb_epochs_done = nb_epochs_done)
+
         log_string('saved_model ' + model_filename)
 
         nb_train_errors = nb_errors(model, train_set)
@@ -550,7 +569,8 @@ for problem_number in map(int, args.problems.split(',')):
                                args.nb_test_samples, args.batch_size,
                                cuda = torch.cuda.is_available())
 
-        nb_test_errors = nb_errors(model, test_set)
+        nb_test_errors = nb_errors(model, test_set,
+                                   mistake_filename_pattern = 'mistake_{:06d}_{:d}.png')
 
         log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
             problem_number,