X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=cnn-svrt.py;h=a6b9cabdb8e1ebbf2c961549bd0764d8c0466e05;hp=966ea4a60262e71e7c6a5fd53347f9580058cb9b;hb=HEAD;hpb=a25efec7618acd54806bd6ce69b30d473b7845f8

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 966ea4a..a6b9cab 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, 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)
 
@@ -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)
@@ -437,7 +442,7 @@ class vignette_logger():
             )
             self.last_t = t
 
-def save_examplar_vignettes(data_set, nb, name):
+def save_exemplar_vignettes(data_set, nb, name):
     n = torch.randperm(data_set.nb_samples).narrow(0, 0, nb)
 
     for k in range(0, nb):
@@ -458,8 +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
@@ -490,7 +493,7 @@ for problem_number in map(int, args.problems.split(',')):
 
     model_filename = model.name + '_pb:' + \
                      str(problem_number) + '_ns:' + \
-                     int_to_suffix(args.nb_train_samples) + '.state'
+                     int_to_suffix(args.nb_train_samples) + '.pth'
 
     nb_parameters = 0
     for p in model.parameters(): nb_parameters += p.numel()
@@ -526,8 +529,8 @@ for problem_number in map(int, args.problems.split(',')):
         )
 
         if args.nb_exemplar_vignettes > 0:
-            save_examplar_vignettes(train_set, args.nb_exemplar_vignettes,
-                                    'examplar_{:d}.png'.format(problem_number))
+            save_exemplar_vignettes(train_set, args.nb_exemplar_vignettes,
+                                    'exemplar_{:d}.png'.format(problem_number))
 
         if args.validation_error_threshold > 0.0:
             validation_set = VignetteSet(problem_number,
@@ -537,7 +540,10 @@ 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)