X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=fab2772e718f0157537da291ea9018ff9b028501;hb=198149a1334feddec21a0a01e7f503ab4396e610;hp=3fe50d8833740354ffe9595c268233adb36a4384;hpb=ffe0b4fed11bb356684d9faa1849c86997a3029a;p=pysvrt.git

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 3fe50d8..fab2772 100755
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -105,6 +105,10 @@ 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()
 
@@ -244,12 +248,13 @@ 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, nb_channels, kernel_size=5, padding=2)
+        self.conv3 = nn.Conv2d(nb_channels, nb_channels, kernel_size=3, padding=1)
+        self.conv4 = nn.Conv2d(nb_channels, nb_channels, kernel_size=3, padding=1)
+        self.conv5 = nn.Conv2d(nb_channels, 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)
 
@@ -272,7 +277,7 @@ 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)
@@ -355,9 +360,10 @@ def nb_errors(model, data_set, mistake_filename_pattern = None):
                     img = input[i].clone()
                     img.sub_(img.min())
                     img.div_(img.max())
-                    torchvision.utils.save_image(img,
-                                                 mistake_filename_pattern.format(b + i, target[i]))
-
+                    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
 
 ######################################################################
@@ -457,8 +463,6 @@ 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
@@ -560,7 +564,7 @@ for problem_number in map(int, args.problems.split(',')):
                                cuda = torch.cuda.is_available())
 
         nb_test_errors = nb_errors(model, test_set,
-                                   mistake_filename_pattern = 'mistake_{:d}_{:06d}.png')
+                                   mistake_filename_pattern = 'mistake_{:06d}_{:d}.png')
 
         log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
             problem_number,