Added persistence of the model parameters.

[pysvrt.git] / cnn-svrt.py

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 3550d85..e7e4574 100755 (executable)
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -23,6 +23,7 @@
 
 import time
 import argparse
+
 from colorama import Fore, Back, Style
 
 import torch
@@ -52,7 +53,7 @@ parser.add_argument('--nb_test_samples',
                     help = 'How many samples for test')
 
 parser.add_argument('--nb_epochs',
-                    type = int, default = 25,
+                    type = int, default = 50,
                     help = 'How many training epochs')
 
 parser.add_argument('--log_file',
@@ -68,8 +69,7 @@ log_file = open(args.log_file, 'w')
 print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL)
 
 def log_string(s):
-    s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + \
-        str(problem_number) + ' ' + s
+    s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + s
     log_file.write(s + '\n')
     log_file.flush()
     print(s)
@@ -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)
 
@@ -89,21 +89,21 @@ def generate_set(p, n):
 
 # Afroze's ShallowNet
 
-#                    map size   nb. maps
-#                  ----------------------
-#                    128x128    1
-# -- conv(21x21)  -> 108x108    6
-# -- max(2x2)     -> 54x54      6
-# -- conv(19x19)  -> 36x36      16
-# -- max(2x2)     -> 18x18      16
-# -- conv(18x18)  -> 1x1        120
-# -- reshape      -> 120        1
-# -- full(120x84) -> 84         1
-# -- full(84x2)   -> 2          1
-
-class Net(nn.Module):
+#                       map size   nb. maps
+#                     ----------------------
+#    input                128x128    1
+# -- conv(21x21 x 6)   -> 108x108    6
+# -- max(2x2)          -> 54x54      6
+# -- conv(19x19 x 16)  -> 36x36      16
+# -- max(2x2)          -> 18x18      16
+# -- conv(18x18 x 120) -> 1x1        120
+# -- reshape           -> 120        1
+# -- full(120x84)      -> 84         1
+# -- full(84x2)        -> 2          1
+
+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
 
@@ -163,23 +157,43 @@ def nb_errors(model, data_input, data_target, bs = 100):
 
 ######################################################################
 
+for arg in vars(args):
+    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 {:.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,
         train_input.size(0))
@@ -187,7 +201,8 @@ for problem_number in range(1, 24):
 
     nb_test_errors = nb_errors(model, test_input, test_target)
 
-    log_string('TEST_ERROR {:.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,
         test_input.size(0))