Open o0t1ng0o opened 4 years ago
Thank you for this repo! First, let me confirm if I got it. Did you re-train our ABN with 12 facial attributes? and did you use the chainer==2.1.0, cupy==1.0.3 and Python2?
Hi, @Hiroshi-Fukui I directly trained ABN with 12 facial attributes. I used chainer == 6.4.0, cupy==6.4.0 and Python3.6. So the model differs extremely when using different environment?
Yes, I only evaluated the old version of chainer , cupy, and python. sorry...
@Hiroshi-Fukui So is it possible to implement in PyTorch?
Hi, @Hiroshi-Fukui I failed to set up the environment. Could you please tell the version of CUDA, cuDNN, nccl, GPU driver and python?
Additionally, can I rewrite the code of multi-task learning based on your code repository (https://github.com/machine-perception-robotics-group/attention_branch_network) which is for image classification? Is it possible to come out the meaningful attention maps for different facial attributes?
Many thanks! I am looking forward to your feedback~
Sorry, I missed the new issues...
Sorry, I forget the versions of CUDA, cuDNN, nccl, GPU driver. The version of python is 2.
But, you can get our chainer environment by docker pull fhiro0125/chainercv_07_
.
Maybe, you can implement the ABN on facial attributes recognition using pytorch. I could implement using ABN image classification model (, but I can't open to the public it on GitHub).
Thanks for your reply~
I tried to pull the environment.
When I use this command docker pull fhiro0125/chainercv_07_
, it comes the error invalid reference format
.
Is there any problem in this command?
Hi, @Hiroshi-Fukui
I successfully get your environment by docker pull fhiro0125/chainercv_07_1
.
But the attention maps are still the same as the images above.
Could you please provide the pretrained model of chainer version?
Very sorry, I lost your message...
I modified this code after submitting the CVPR paper. I forget the modification, sorry...
Please try to add the two lines to test.py
. I removed the normalizing process of an attention map.
min_att = 0
max_att = 30
...
item_attention = (item_attention - min_att) / (max_att - min_att)
When I add the lines, I can get the correct attention map like CVPR and arXiv papers.
(Please adjust the value of max_att
. In CelebA, 30 is the best value.)
Hi, @Hiroshi-Fukui
Thanks you for sharing this code about the multi-task!
I tried this code for 12 facial attributes. But I found that the attention map is almost useless. Here are the attention maps which are generated by test.py.
Bald:
Bangs:
Big Lips:
Big Nose:
Black Hair:
Blond Hair:
Blurry:
Brown Hair:
Input image:
![input](https://user-images.githubusercontent.com/16815652/66248357-77873a00-e758-11e9-818a-5e45ac73290c.png)
Is there any problem in your code? Could you please give me advice? Many thanks!