X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=06e58bd82590e5f6b066ad80e7c138d5e4c4f754;hb=74a872447b15747c7eb576b24344ed6b48d01642;hp=aa3690d13c800122d7599d41172e19f141cb48d1;hpb=f829e951a7988cfc228af56fbcf17057cb61c06c;p=pysvrt.git

diff --git a/cnn-svrt.py b/cnn-svrt.py
index aa3690d..06e58bd 100755
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -73,6 +73,10 @@ parser.add_argument('--compress_vignettes',
                     action='store_true', default = False,
                     help = 'Use lossless compression to reduce the memory footprint')
 
+parser.add_argument('--test_loaded_models',
+                    action='store_true', default = False,
+                    help = 'Should we compute the test error of models we load')
+
 args = parser.parse_args()
 
 ######################################################################
@@ -142,6 +146,8 @@ def train_model(model, train_set):
 
     optimizer = optim.SGD(model.parameters(), lr = 1e-2)
 
+    start_t = time.time()
+
     for e in range(0, args.nb_epochs):
         acc_loss = 0.0
         for b in range(0, train_set.nb_batches):
@@ -153,6 +159,8 @@ def train_model(model, train_set):
             loss.backward()
             optimizer.step()
         log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss))
+        dt = (time.time() - t) / (e + 1)
+        print(Fore.CYAN + 'ETA ' + time.ctime(time.time() + dt * (args.nb_epochs - e)) + Style.RESET_ALL)
 
     return model
 
@@ -180,6 +188,8 @@ for arg in vars(args):
 
 for problem_number in range(1, 24):
 
+    log_string('**** problem ' + str(problem_number) + ' ****')
+
     model = AfrozeShallowNet()
 
     if torch.cuda.is_available():
@@ -210,20 +220,12 @@ for problem_number in range(1, 24):
             train_set = CompressedVignetteSet(problem_number,
                                               args.nb_train_batches, args.batch_size,
                                               cuda=torch.cuda.is_available())
-            test_set = CompressedVignetteSet(problem_number,
-                                             args.nb_test_batches, args.batch_size,
-                                             cuda=torch.cuda.is_available())
         else:
             train_set = VignetteSet(problem_number,
                                     args.nb_train_batches, args.batch_size,
                                     cuda=torch.cuda.is_available())
-            test_set = VignetteSet(problem_number,
-                                   args.nb_test_batches, args.batch_size,
-                                   cuda=torch.cuda.is_available())
 
-        log_string('data_generation {:0.2f} samples / s'.format(
-            (train_set.nb_samples + test_set.nb_samples) / (time.time() - t))
-        )
+        log_string('data_generation {:0.2f} samples / s'.format(train_set.nb_samples / (time.time() - t)))
 
         train_model(model, train_set)
         torch.save(model.state_dict(), model_filename)
@@ -238,6 +240,21 @@ for problem_number in range(1, 24):
             train_set.nb_samples)
         )
 
+    if need_to_train or args.test_loaded_models:
+
+        t = time.time()
+
+        if args.compress_vignettes:
+            test_set = CompressedVignetteSet(problem_number,
+                                             args.nb_test_batches, args.batch_size,
+                                             cuda=torch.cuda.is_available())
+        else:
+            test_set = VignetteSet(problem_number,
+                                   args.nb_test_batches, args.batch_size,
+                                   cuda=torch.cuda.is_available())
+
+        log_string('data_generation {:0.2f} samples / s'.format(test_set.nb_samples / (time.time() - t)))
+
         nb_test_errors = nb_errors(model, test_set)
 
         log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(