search

CSAILVision / places365

The Places365-CNNs for Scene Classification
http://places2.csail.mit.edu/
MIT License
1.92k stars 536 forks source link

Which channel order: RGB or BGR #30

Closed GrumpyZhou closed 7 years ago

GrumpyZhou commented 7 years ago

Hi,
I want to use your models as pre-trained weight for other tasks. However, I am not sure how you processed your input images, as I saw you have :

  1. ResNet152-places365 fine-tuned from ResNet152-ImageNet
  2. ResNet152-places365 trained from scratch using Torch

As the author of ResNet152-ImageNet, mentioned that he used BGR, which is expected if using caffe... So i guess the model in 1, should also use BGR? While the model in 2 is not clear to me, as it was trained from scratch and used Torch...

It would be nice if you can tell me it directly. Thanks!

zhoubolei commented 7 years ago

Resnet trained from scratch using RGB order.

Sent from my iPhone

On Sep 19, 2017, at 5:04 PM, Qunjie Zhou notifications@github.com wrote:

Hi, I want to use your models as pre-trained weight for other tasks. However, I am not sure how you processed your input images, as I saw you have :

ResNet152-places365 fine-tuned from ResNet152-ImageNet ResNet152-places365 trained from scratch using Torch As the author of ResNet152-ImageNet, mentioned that he used BGR, which is expected if using caffe... So i guess the model in 1, should also use BGR? While the model in 2 is not clear to me, as it was trained from scratch and used Torch...

It would be nice if you can tell me it directly. Thanks!

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.