CSAILVision / CSAILVision/places365
preprocess input image
Open
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 538
- PR merge metrics
- No merged PRs in 30d
Description
Hello!
I download the VGG16-places365 weights, and then convert it to pytorch-format. I note you say 'that the input image scale should be from 0-255'. Should I swap the channels into BGR then subtract imagenet
means which is [103.939, 116.779, 123.68]?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.