Skip to content
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.

Sign up for GitHub

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

Jump to bottom

typo fix #745

Open
wants to merge 1 commit into
base: pytorch-1.0
Choose a base branch
from
Open

typo fix #745

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ During our implementing, we referred the above implementations, especially [long

* **It supports three pooling methods**. We integrate three pooling methods: roi pooing, roi align and roi crop. More importantly, we modify all of them to support multi-image batch training.

* **It is memory efficient**. We limit the image aspect ratio, and group images with similar aspect ratios into a minibatch. As such, we can train resnet101 and VGG16 with batchsize = 4 (4 images) on a sigle Titan X (12 GB). When training with 8 GPU, the maximum batchsize for each GPU is 3 (Res101), totally 24.
* **It is memory efficient**. We limit the image aspect ratio, and group images with similar aspect ratios into a minibatch. As such, we can train resnet101 and VGG16 with batchsize = 4 (4 images) on a single Titan X (12 GB). When training with 8 GPUs, the maximum batchsize for each GPU is 3 (Res101), totaling 24.

* **It is faster**. Based on the above modifications, the training is much faster. We report the training speed on NVIDIA TITAN Xp in the tables below.

Expand Down