X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=cnn-svrt.py;h=694f035edde45339823fef4e1671ec241e0a00e2;hp=084606aa67b18191a969043c214e075d22825fe0;hb=abbbb61852f54e90df6ac5b5f4dcb71d06f88f49;hpb=c71899cfec905c50302be54725a97d7fbff08f54

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 084606a..694f035 100755
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -27,6 +27,8 @@ import math
 
 from colorama import Fore, Back, Style
 
+# Pytorch
+
 import torch
 
 from torch import optim
@@ -36,6 +38,8 @@ from torch import nn
 from torch.nn import functional as fn
 from torchvision import datasets, transforms, utils
 
+# SVRT
+
 from vignette_set import VignetteSet, CompressedVignetteSet
 
 ######################################################################
@@ -107,6 +111,7 @@ class AfrozeShallowNet(nn.Module):
         self.conv3 = nn.Conv2d(16, 120, kernel_size=18)
         self.fc1 = nn.Linear(120, 84)
         self.fc2 = nn.Linear(84, 2)
+        self.name = 'shallownet'
 
     def forward(self, x):
         x = fn.relu(fn.max_pool2d(self.conv1(x), kernel_size=2))
@@ -117,6 +122,8 @@ class AfrozeShallowNet(nn.Module):
         x = self.fc2(x)
         return x
 
+######################################################################
+
 def train_model(model, train_set):
     batch_size = args.batch_size
     criterion = nn.CrossEntropyLoss()
@@ -160,51 +167,75 @@ def nb_errors(model, data_set):
 for arg in vars(args):
     log_string('argument ' + str(arg) + ' ' + str(getattr(args, arg)))
 
+######################################################################
+
 for problem_number in range(1, 24):
-    if args.compress_vignettes:
-        train_set = CompressedVignetteSet(problem_number, args.nb_train_batches, args.batch_size)
-        test_set = CompressedVignetteSet(problem_number, args.nb_test_batches, args.batch_size)
-    else:
-        train_set = VignetteSet(problem_number, args.nb_train_batches, args.batch_size)
-        test_set = VignetteSet(problem_number, args.nb_test_batches, args.batch_size)
 
     model = AfrozeShallowNet()
 
     if torch.cuda.is_available():
         model.cuda()
 
+    model_filename = model.name + '_' + \
+                     str(problem_number) + '_' + \
+                     str(args.nb_train_batches) + '.param'
+
     nb_parameters = 0
-    for p in model.parameters():
-        nb_parameters += p.numel()
+    for p in model.parameters(): nb_parameters += p.numel()
     log_string('nb_parameters {:d}'.format(nb_parameters))
 
-    model_filename = 'model_' + str(problem_number) + '.param'
-
+    need_to_train = False
     try:
         model.load_state_dict(torch.load(model_filename))
         log_string('loaded_model ' + model_filename)
     except:
-        log_string('training_model')
+        need_to_train = True
+
+    if need_to_train:
+
+        log_string('training_model ' + model_filename)
+
+        t = time.time()
+
+        if args.compress_vignettes:
+            train_set = CompressedVignetteSet(problem_number,
+                                              args.nb_train_batches, args.batch_size,
+                                              cuda=torch.cuda.is_available())
+            test_set = CompressedVignetteSet(problem_number,
+                                             args.nb_test_batches, args.batch_size,
+                                             cuda=torch.cuda.is_available())
+        else:
+            train_set = VignetteSet(problem_number,
+                                    args.nb_train_batches, args.batch_size,
+                                    cuda=torch.cuda.is_available())
+            test_set = VignetteSet(problem_number,
+                                   args.nb_test_batches, args.batch_size,
+                                   cuda=torch.cuda.is_available())
+
+        log_string('data_generation {:0.2f} samples / s'.format(
+            (train_set.nb_samples + test_set.nb_samples) / (time.time() - t))
+        )
+
         train_model(model, train_set)
         torch.save(model.state_dict(), model_filename)
         log_string('saved_model ' + model_filename)
 
-    nb_train_errors = nb_errors(model, train_set)
+        nb_train_errors = nb_errors(model, train_set)
 
-    log_string('train_error {:d} {:.02f}% {:d} {:d}'.format(
-        problem_number,
-        100 * nb_train_errors / train_set.nb_samples,
-        nb_train_errors,
-        train_set.nb_samples)
-    )
+        log_string('train_error {:d} {:.02f}% {:d} {:d}'.format(
+            problem_number,
+            100 * nb_train_errors / train_set.nb_samples,
+            nb_train_errors,
+            train_set.nb_samples)
+        )
 
-    nb_test_errors = nb_errors(model, test_set)
+        nb_test_errors = nb_errors(model, test_set)
 
-    log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
-        problem_number,
-        100 * nb_test_errors / test_set.nb_samples,
-        nb_test_errors,
-        test_set.nb_samples)
-    )
+        log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
+            problem_number,
+            100 * nb_test_errors / test_set.nb_samples,
+            nb_test_errors,
+            test_set.nb_samples)
+        )
 
 ######################################################################