X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=cnn-svrt.py;h=96fb498740625c551a3524df7e79ef68e35544ee;hp=79d3ff462d6c6d6ea7e2d3114568d2d6ba6c5c09;hb=231c2b2d912d7480af0ce9512b12a909a4fe2a3d;hpb=44363bdf89bf78a62776129c4a5f97ad6a360293

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 79d3ff4..96fb498 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
@@ -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 = 100,
                     help = 'How many training epochs')
 
 parser.add_argument('--log_file',
@@ -65,11 +66,10 @@ args = parser.parse_args()
 
 log_file = open(args.log_file, 'w')
 
-print('Logging into ' + args.log_file)
+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)
@@ -87,20 +87,34 @@ def generate_set(p, n):
 
 ######################################################################
 
-# 128x128 --conv(9)-> 120x120 --max(4)-> 30x30 --conv(6)-> 25x25 --max(5)-> 5x5
+# Afroze's ShallowNet
+
+#                       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 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
@@ -108,6 +122,11 @@ class Net(nn.Module):
 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))
+
     if torch.cuda.is_available():
         model.cuda()
         criterion.cuda()
@@ -144,9 +163,10 @@ def nb_errors(model, data_input, data_target, bs = 100):
 
 ######################################################################
 
-# for problem_number in range(1, 24):
+for arg in vars(args):
+    log_string('ARGUMENT ' + str(arg) + ' ' + str(getattr(args, arg)))
 
-for problem_number in [ 3 ]:
+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)
 
@@ -162,7 +182,8 @@ for problem_number in [ 3 ]:
 
     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))
@@ -170,7 +191,8 @@ for problem_number in [ 3 ]:
 
     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))