residual-attention-network

residual-attention-network copied to clipboard

Do you train imagenet with batch size 64 too? It goes out of memory on 1080 Ti.

2

yxchng

Thanks for your great job! I have a question about the expression of mix attention and how to implement it. And is conv->relu->conv->sigmoid able to represent?

fengshenfeilian

Visualizing the Attention Masks

2

Hi, I wanted to ask how to visualize the attention masks as given in Fig 1 in the paper? Does it involve using GRAD CAM? or is it directly the...

jain-avi

Hi, i am intereated in your work and want to fine-tune the model for other task, could you please share the pre-trained imagenet model?

wpl18589946597

GPU memory

15

You mentioned in the paper that the batch size for training is 32. However for my GPU which has 8G I set the batch size to 8 and almost all...

melody-rain

Hi, i am intereated in your work and want to fine-tune the model for other task, could you please share the pre-trained imagenet model?

5

chengyuz

Please tell me how about the settings in BN layers in training phase. think you!

zallmight

compile your caffe code success but init a net from python caffe with your proto get error

3

import caffe affe.set_mode_gpu() net = caffe.Net("/path-to/Attention-56-dcase.prototxt",caffe.TRAIN) got error: I1207 11:37:31.168298 31752 layer_factory.hpp:77] Creating layer conv1/bn F1207 11:37:31.168318 31752 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type:...

hackerekcah

make: *** [.build_release/cuda/src/caffe/util/interp.o] 错误 1 make: *** 正在等待未完成的任务.... nvcc warning : The 'compute_20', 'sm_20', and 'sm_21' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to...

wjzh1

Hi, Many thanks for your excellent works! I want to train your network, can you please release the train prototxt? Best,

hungsing92