X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=cnn-svrt.py;h=d0704fff48c85fca80c5723c20cb369c0600a013;hp=cb94184b678870912aaafe37fbb5e5b04a36f8a1;hb=4c77eebce3c3914a58c548c606d045efdae2284a;hpb=b3c335857859d457575128690e4aa77f52d17e5c

diff --git a/cnn-svrt.py b/cnn-svrt.py
index cb94184..d0704ff 100755
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -24,8 +24,10 @@
 import time
 import argparse
 import math
+
 import distutils.util
 import re
+import signal
 
 from colorama import Fore, Back, Style
 
@@ -83,6 +85,9 @@ parser.add_argument('--compress_vignettes',
                     type = distutils.util.strtobool, default = 'True',
                     help = 'Use lossless compression to reduce the memory footprint')
 
+parser.add_argument('--save_test_mistakes',
+                    type = distutils.util.strtobool, default = 'False')
+
 parser.add_argument('--model',
                     type = str, default = 'deepnet',
                     help = 'What model to use')
@@ -100,6 +105,10 @@ args = parser.parse_args()
 ######################################################################
 
 log_file = open(args.log_file, 'a')
+log_file.write('\n')
+log_file.write('@@@@@@@@@@@@@@@@@@@ ' + time.ctime() + ' @@@@@@@@@@@@@@@@@@@\n')
+log_file.write('\n')
+
 pred_log_t = None
 last_tag_t = time.time()
 
@@ -127,7 +136,24 @@ def log_string(s, remark = ''):
     log_file.write(re.sub(' ', '_', time.ctime()) + ' ' + elapsed + ' ' + s + '\n')
     log_file.flush()
 
-    print(Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s + Fore.CYAN + remark + Style.RESET_ALL)
+    print(Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed \
+          + Style.RESET_ALL
+          + ' ' \
+          + s + Fore.CYAN + remark \
+          + Style.RESET_ALL)
+
+######################################################################
+
+def handler_sigint(signum, frame):
+    log_string('got sigint')
+    exit(0)
+
+def handler_sigterm(signum, frame):
+    log_string('got sigterm')
+    exit(0)
+
+signal.signal(signal.SIGINT, handler_sigint)
+signal.signal(signal.SIGTERM, handler_sigterm)
 
 ######################################################################
 
@@ -268,17 +294,17 @@ class DeepNet3(nn.Module):
     name = 'deepnet3'
 
     def __init__(self):
-        super(DeepNet2, self).__init__()
+        super(DeepNet3, self).__init__()
         self.conv1 = nn.Conv2d(  1,  32, kernel_size=7, stride=4, padding=3)
-        self.conv2 = nn.Conv2d( 32, 256, kernel_size=5, padding=2)
-        self.conv3 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.conv4 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.conv5 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.conv6 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.conv7 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
-        self.fc1 = nn.Linear(4096, 512)
-        self.fc2 = nn.Linear(512, 512)
-        self.fc3 = nn.Linear(512, 2)
+        self.conv2 = nn.Conv2d( 32, 128, kernel_size=5, padding=2)
+        self.conv3 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
+        self.conv4 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
+        self.conv5 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
+        self.conv6 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
+        self.conv7 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
+        self.fc1 = nn.Linear(2048, 256)
+        self.fc2 = nn.Linear(256, 256)
+        self.fc3 = nn.Linear(256, 2)
 
     def forward(self, x):
         x = self.conv1(x)
@@ -305,7 +331,7 @@ class DeepNet3(nn.Module):
         x = self.conv7(x)
         x = fn.relu(x)
 
-        x = x.view(-1, 4096)
+        x = x.view(-1, 2048)
 
         x = self.fc1(x)
         x = fn.relu(x)
@@ -319,7 +345,7 @@ class DeepNet3(nn.Module):
 
 ######################################################################
 
-def nb_errors(model, data_set):
+def nb_errors(model, data_set, mistake_filename_pattern = None):
     ne = 0
     for b in range(0, data_set.nb_batches):
         input, target = data_set.get_batch(b)
@@ -329,7 +355,14 @@ def nb_errors(model, data_set):
         for i in range(0, data_set.batch_size):
             if wta_prediction[i] != target[i]:
                 ne = ne + 1
-
+                if mistake_filename_pattern is not None:
+                    img = input[i].clone()
+                    img.sub_(img.min())
+                    img.div_(img.max())
+                    k = b * data_set.batch_size + i
+                    filename = mistake_filename_pattern.format(k, target[i])
+                    torchvision.utils.save_image(img, filename)
+                    print(Fore.RED + 'Wrote ' + filename + Style.RESET_ALL)
     return ne
 
 ######################################################################
@@ -429,8 +462,6 @@ if args.nb_train_samples%args.batch_size > 0 or args.nb_test_samples%args.batch_
     print('The number of samples must be a multiple of the batch size.')
     raise
 
-log_string('############### start ###############')
-
 if args.compress_vignettes:
     log_string('using_compressed_vignettes')
     VignetteSet = svrtset.CompressedVignetteSet
@@ -531,7 +562,8 @@ for problem_number in map(int, args.problems.split(',')):
                                args.nb_test_samples, args.batch_size,
                                cuda = torch.cuda.is_available())
 
-        nb_test_errors = nb_errors(model, test_set)
+        nb_test_errors = nb_errors(model, test_set,
+                                   mistake_filename_pattern = 'mistake_{:06d}_{:d}.png')
 
         log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
             problem_number,