X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=cnn-svrt.py;h=1d5e887c832f59cbb9d56317f3413ba4d24dbe03;hb=3f3a2df9cb54730206a94a294d60d48422333a11;hp=755d1c7bf1afcd74f4d5957e682d5d7bfe74c2e3;hpb=1b19eb14d0bd617deacfb7d15aa2e7babad3a5a7;p=pysvrt.git

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 755d1c7..1d5e887 100755
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -23,6 +23,7 @@
 
 import time
 import argparse
+from colorama import Fore, Back, Style
 
 import torch
 
@@ -54,14 +55,21 @@ parser.add_argument('--nb_epochs',
                     type = int, default = 25,
                     help = 'How many training epochs')
 
+parser.add_argument('--log_file',
+                    type = str, default = 'cnn-svrt.log',
+                    help = 'Log file name')
+
 args = parser.parse_args()
 
 ######################################################################
 
-log_file = open('cnn-svrt.log', 'w')
+log_file = open(args.log_file, 'w')
+
+print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL)
 
 def log_string(s):
-    s = time.ctime() + ' ' + str(problem_number) + ' | ' + s
+    s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + \
+        str(problem_number) + ' ' + s
     log_file.write(s + '\n')
     log_file.flush()
     print(s)
@@ -70,26 +78,43 @@ def log_string(s):
 
 def generate_set(p, n):
     target = torch.LongTensor(n).bernoulli_(0.5)
+    t = time.time()
     input = svrt.generate_vignettes(p, target)
+    t = time.time() - 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)
 
 ######################################################################
 
-# 128x128 --conv(9)-> 120x120 --max(4)-> 30x30 --conv(6)-> 25x25 --max(5)-> 5x5
+# 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):
     def __init__(self):
         super(Net, self).__init__()
-        self.conv1 = nn.Conv2d(1, 10, kernel_size=9)
-        self.conv2 = nn.Conv2d(10, 20, kernel_size=6)
-        self.fc1 = nn.Linear(500, 100)
-        self.fc2 = nn.Linear(100, 2)
+        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)
+        self.fc1 = nn.Linear(120, 84)
+        self.fc2 = nn.Linear(84, 2)
 
     def forward(self, x):
-        x = fn.relu(fn.max_pool2d(self.conv1(x), kernel_size=4, stride=4))
-        x = fn.relu(fn.max_pool2d(self.conv2(x), kernel_size=5, stride=5))
-        x = x.view(-1, 500)
+        x = fn.relu(fn.max_pool2d(self.conv1(x), kernel_size=2))
+        x = fn.relu(fn.max_pool2d(self.conv2(x), kernel_size=2))
+        x = fn.relu(self.conv3(x))
+        x = x.view(-1, 120)
         x = fn.relu(self.fc1(x))
         x = self.fc2(x)
         return x
@@ -101,7 +126,7 @@ def train_model(train_input, train_target):
         model.cuda()
         criterion.cuda()
 
-    optimizer, bs = optim.SGD(model.parameters(), lr = 1e-1), 100
+    optimizer, bs = optim.SGD(model.parameters(), lr = 1e-2), 100
 
     for k in range(0, args.nb_epochs):
         acc_loss = 0.0
@@ -147,9 +172,17 @@ for problem_number in range(1, 24):
 
     model = train_model(train_input, train_target)
 
+    nb_train_errors = nb_errors(model, train_input, train_target)
+
+    log_string('TRAIN_ERROR {:.02f}% {:d} {:d}'.format(
+        100 * nb_train_errors / train_input.size(0),
+        nb_train_errors,
+        train_input.size(0))
+    )
+
     nb_test_errors = nb_errors(model, test_input, test_target)
 
-    log_string('TEST_ERROR {:.02f}% ({:d}/{:d})'.format(
+    log_string('TEST_ERROR {:.02f}% {:d} {:d}'.format(
         100 * nb_test_errors / test_input.size(0),
         nb_test_errors,
         test_input.size(0))