Added persistence of the model parameters.

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 3e20f8e..e7e4574 100755 (executable)
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -81,7 +81,7 @@ def generate_set(p, n):
     t = time.time()
     input = svrt.generate_vignettes(p, target)
     t = time.time() - t
-    log_string('DATA_SET_GENERATION {:.02f} sample/s'.format(n / t))
+    log_string('data_set_generation {:.02f} sample/s'.format(n / t))
     input = input.view(input.size(0), 1, input.size(1), input.size(2)).float()
     return Variable(input), Variable(target)
 
@@ -101,9 +101,9 @@ def generate_set(p, n):
 # -- full(120x84)      -> 84         1
 # -- full(84x2)        -> 2          1
 
-class Net(nn.Module):
+class AfrozeShallowNet(nn.Module):
     def __init__(self):
-        super(Net, self).__init__()
+        super(AfrozeShallowNet, self).__init__()
         self.conv1 = nn.Conv2d(1, 6, kernel_size=21)
         self.conv2 = nn.Conv2d(6, 16, kernel_size=19)
         self.conv3 = nn.Conv2d(16, 120, kernel_size=18)
@@ -119,16 +119,10 @@ class Net(nn.Module):
         x = self.fc2(x)
         return x
 
-def train_model(train_input, train_target):
-    model, criterion = Net(), nn.CrossEntropyLoss()
-
-    nb_parameters = 0
-    for p in model.parameters():
-        nb_parameters += p.numel()
-    log_string('NB_PARAMETERS {:d}'.format(nb_parameters))
+def train_model(model, train_input, train_target):
+    criterion = nn.CrossEntropyLoss()
 
     if torch.cuda.is_available():
-        model.cuda()
         criterion.cuda()
 
     optimizer, bs = optim.SGD(model.parameters(), lr = 1e-2), 100
@@ -142,7 +136,7 @@ def train_model(train_input, train_target):
             model.zero_grad()
             loss.backward()
             optimizer.step()
-        log_string('TRAIN_LOSS {:d} {:f}'.format(k, acc_loss))
+        log_string('train_loss {:d} {:f}'.format(k, acc_loss))
 
     return model
 
@@ -164,25 +158,41 @@ def nb_errors(model, data_input, data_target, bs = 100):
 ######################################################################
 
 for arg in vars(args):
-    log_string('ARGUMENT ' + str(arg) + ' ' + str(getattr(args, arg)))
+    log_string('argument ' + str(arg) + ' ' + str(getattr(args, arg)))
 
 for problem_number in range(1, 24):
     train_input, train_target = generate_set(problem_number, args.nb_train_samples)
     test_input, test_target = generate_set(problem_number, args.nb_test_samples)
+    model = AfrozeShallowNet()
 
     if torch.cuda.is_available():
         train_input, train_target = train_input.cuda(), train_target.cuda()
         test_input, test_target = test_input.cuda(), test_target.cuda()
+        model.cuda()
 
     mu, std = train_input.data.mean(), train_input.data.std()
     train_input.data.sub_(mu).div_(std)
     test_input.data.sub_(mu).div_(std)
 
-    model = train_model(train_input, train_target)
+    nb_parameters = 0
+    for p in model.parameters():
+        nb_parameters += p.numel()
+    log_string('nb_parameters {:d}'.format(nb_parameters))
+
+    model_filename = 'model_' + str(problem_number) + '.param'
+
+    try:
+        model.load_state_dict(torch.load(model_filename))
+        log_string('loaded_model ' + model_filename)
+    except:
+        log_string('training_model')
+        train_model(model, train_input, train_target)
+        torch.save(model.state_dict(), model_filename)
+        log_string('saved_model ' + model_filename)
 
     nb_train_errors = nb_errors(model, train_input, train_target)
 
-    log_string('TRAIN_ERROR {:d} {:.02f}% {:d} {:d}'.format(
+    log_string('train_error {:d} {:.02f}% {:d} {:d}'.format(
         problem_number,
         100 * nb_train_errors / train_input.size(0),
         nb_train_errors,
@@ -191,7 +201,7 @@ for problem_number in range(1, 24):
 
     nb_test_errors = nb_errors(model, test_input, test_target)
 
-    log_string('TEST_ERROR {:d} {:.02f}% {:d} {:d}'.format(
+    log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
         problem_number,
         100 * nb_test_errors / test_input.size(0),
         nb_test_errors,