-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add slowfast model to video classification #4815
Conversation
dygraph/slowfast/train.py
Outdated
) | ||
|
||
use_data_parallel = args.use_data_parallel | ||
place = fluid.CUDAPlace(fluid.dygraph.parallel.Env().dev_id) \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
can it suport cpu device?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
for batch_id, data in enumerate(train_loader): | ||
batch_reader_end = time.time() | ||
y_data = data[2] | ||
labels = to_variable(y_data) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
to_variable之后,网络之前,建议添加个耗时统计,对于性能优化预计有较大帮助
dygraph/slowfast/eval.py
Outdated
parser.add_argument( | ||
'--weights', | ||
type=str, | ||
default="checkpoints/slowfast_epoch195", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
default is None?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
add slowfast model to video classification