Compute the test error when the network is loaded and not trained.

[pysvrt.git] / cnn-svrt.py

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 7bef242..283f02b 100755 (executable)
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -78,11 +78,20 @@ args = parser.parse_args()
 ######################################################################
 
 log_file = open(args.log_file, 'w')
+pred_log_t = None
 
 print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL)
 
 def log_string(s):
-    s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + s
+    global pred_log_t
+    t = time.time()
+
+    if pred_log_t is None:
+        elapsed = 'start'
+    else:
+        elapsed = '+{:.02f}s'.format(t - pred_log_t)
+    pred_log_t = t
+    s = Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s
     log_file.write(s + '\n')
     log_file.flush()
     print(s)
@@ -171,6 +180,8 @@ 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():
@@ -184,29 +195,31 @@ for problem_number in range(1, 24):
     for p in model.parameters(): nb_parameters += p.numel()
     log_string('nb_parameters {:d}'.format(nb_parameters))
 
+    need_to_train = False
     try:
-
         model.load_state_dict(torch.load(model_filename))
         log_string('loaded_model ' + model_filename)
-
     except:
+        need_to_train = True
+
+    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_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))
+        )
 
         train_model(model, train_set)
         torch.save(model.state_dict(), model_filename)
@@ -221,13 +234,23 @@ for problem_number in range(1, 24):
             train_set.nb_samples)
         )
 
-        nb_test_errors = nb_errors(model, test_set)
+    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())
+
+    nb_test_errors = nb_errors(model, test_set)
+
+    log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
+        problem_number,
+        100 * nb_test_errors / test_set.nb_samples,
+        nb_test_errors,
+        test_set.nb_samples)
+    )
 
-        log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
-            problem_number,
-            100 * nb_test_errors / test_set.nb_samples,
-            nb_test_errors,
-            test_set.nb_samples)
-        )
 
 ######################################################################