projects
/
pysvrt.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Heavy fix.
[pysvrt.git]
/
cnn-svrt.py
diff --git
a/cnn-svrt.py
b/cnn-svrt.py
index
6645ac1
..
694f035
100755
(executable)
--- a/
cnn-svrt.py
+++ b/
cnn-svrt.py
@@
-171,28
+171,32
@@
for arg in vars(args):
for problem_number in range(1, 24):
for problem_number in range(1, 24):
- model_filename = model.name + '_' + \
- str(problem_number) + '_' + \
- str(args.nb_train_batches) + '.param'
-
model = AfrozeShallowNet()
if torch.cuda.is_available():
model.cuda()
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()
log_string('nb_parameters {:d}'.format(nb_parameters))
nb_parameters = 0
for p in model.parameters(): nb_parameters += p.numel()
log_string('nb_parameters {:d}'.format(nb_parameters))
+ need_to_train = False
try:
try:
-
model.load_state_dict(torch.load(model_filename))
log_string('loaded_model ' + model_filename)
model.load_state_dict(torch.load(model_filename))
log_string('loaded_model ' + model_filename)
-
except:
except:
+ need_to_train = True
+
+ if need_to_train:
log_string('training_model ' + model_filename)
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,
if args.compress_vignettes:
train_set = CompressedVignetteSet(problem_number,
args.nb_train_batches, args.batch_size,
@@
-208,6
+212,10
@@
for problem_number in range(1, 24):
args.nb_test_batches, args.batch_size,
cuda=torch.cuda.is_available())
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)
train_model(model, train_set)
torch.save(model.state_dict(), model_filename)
log_string('saved_model ' + model_filename)