X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=cfef09da934fb5d82181715f428dab1a261d04ba;hb=37030c396217cfe89f8dfa2b9e10ff1ec783a5a7;hp=5dc91c82e66e99322ee77ec95e6e8c4b337dcdff;hpb=15f2d2cf0a655234cfa435789e26238b95f5a371;p=pysvrt.git

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 5dc91c8..cfef09d 100755
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -40,7 +40,7 @@ from torchvision import datasets, transforms, utils
 
 # SVRT
 
-from vignette_set import VignetteSet, CompressedVignetteSet
+import vignette_set
 
 ######################################################################
 
@@ -255,9 +255,9 @@ for arg in vars(args):
 ######################################################################
 
 def int_to_suffix(n):
-    if n > 1000000 and n%1000000 == 0:
+    if n >= 1000000 and n%1000000 == 0:
         return str(n//1000000) + 'M'
-    elif n > 1000 and n%1000 == 0:
+    elif n >= 1000 and n%1000 == 0:
         return str(n//1000) + 'K'
     else:
         return str(n)
@@ -268,26 +268,33 @@ 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
 
+if args.compress_vignettes:
+    VignetteSet = vignette_set.CompressedVignetteSet
+else:
+    VignetteSet = vignette_set.VignetteSet
+
 for problem_number in range(1, 24):
 
-    log_string('**** problem ' + str(problem_number) + ' ****')
+    log_string('############### problem ' + str(problem_number) + ' ###############')
 
     if args.deep_model:
         model = AfrozeDeepNet()
     else:
         model = AfrozeShallowNet()
 
-    if torch.cuda.is_available():
-        model.cuda()
+    if torch.cuda.is_available(): model.cuda()
 
-    model_filename = model.name + '_' + \
-                     str(problem_number) + '_' + \
+    model_filename = model.name + '_pb:' + \
+                     str(problem_number) + '_ns:' + \
                      int_to_suffix(args.nb_train_samples) + '.param'
 
     nb_parameters = 0
     for p in model.parameters(): nb_parameters += p.numel()
     log_string('nb_parameters {:d}'.format(nb_parameters))
 
+    ##################################################
+    # Tries to load the model
+
     need_to_train = False
     try:
         model.load_state_dict(torch.load(model_filename))
@@ -295,20 +302,18 @@ for problem_number in range(1, 24):
     except:
         need_to_train = True
 
+    ##################################################
+    # Train if necessary
+
     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_samples, args.batch_size,
-                                              cuda = torch.cuda.is_available())
-        else:
-            train_set = VignetteSet(problem_number,
-                                    args.nb_train_samples, args.batch_size,
-                                    cuda = torch.cuda.is_available())
+        train_set = VignetteSet(problem_number,
+                                args.nb_train_samples, args.batch_size,
+                                cuda = torch.cuda.is_available())
 
         log_string('data_generation {:0.2f} samples / s'.format(
             train_set.nb_samples / (time.time() - t))
@@ -327,18 +332,16 @@ for problem_number in range(1, 24):
             train_set.nb_samples)
         )
 
+    ##################################################
+    # Test if necessary
+
     if need_to_train or args.test_loaded_models:
 
         t = time.time()
 
-        if args.compress_vignettes:
-            test_set = CompressedVignetteSet(problem_number,
-                                             args.nb_test_samples, args.batch_size,
-                                             cuda = torch.cuda.is_available())
-        else:
-            test_set = VignetteSet(problem_number,
-                                   args.nb_test_samples, args.batch_size,
-                                   cuda = torch.cuda.is_available())
+        test_set = VignetteSet(problem_number,
+                               args.nb_test_samples, args.batch_size,
+                               cuda = torch.cuda.is_available())
 
         log_string('data_generation {:0.2f} samples / s'.format(
             test_set.nb_samples / (time.time() - t))