Boatsure

Hi @Dannyxu1031 have you figured the issue out? I find that the _NoneType_ problem comes from the visibilities--labels--duration and finally turns out to be the _predictions_ dict not including the...

And the same problem happen to CUDA 10.2 as well

自然是可以的，只需要修改一下第一个卷积层的channel数。 我理解这样做唯一的好处是，模型要求输入单通道的灰度图的话，在后面测试的时候可以将这些单通道图concat起来类似mini-batch，进行批测试，使得每一个通道的输出都是每个样本的类别结果。如果模型输入RGB三通道图的话就没法concat，只能一张图一张图的测试。

I searched the website of lfw(http://vis-www.cs.umass.edu/lfw/) and and found several packages of dataset. The _lfw-deepfunneled_ have a size of 250x250, which i guss doesn't match the _lfw-align-128_ . Would you...

@garg-7 Thanks! The baidu link (password: b2ec) works for me. But would you please explain what does CASIA-maxpy-clean-crop-144 mean and what's the structure of train/val_data_13939.txt ? I download the CASIA-WebFace...

@garg-7 In the config.py line 15 and 16: `train_list = '/data/Datasets/webface/train_data_13938.txt'` `val_list = '/data/Datasets/webface/val_data_13938.txt` They don't exist in this repo and that's where I'm confused. I want to transfer the...

@garg-7 Thanks all the same. I'm reading the source code trying to speculate the directory structure of the training set. And yeah, this is the detail only @ronghuaiyang knows but...

Now i have done a project on my custom dataset with this code, and wonder why i asked such a stupid question back here. Don't stick to face recognition, this...

我已经用这份代码做完了一个分类任务，没理解错的话ArcMarginProduct类本质上就是一个全连接层，就像原码里那样，将model的输出再送进metric_fc层就好了，做人脸的分类还是其他的分类都一样。

same problem， downgrade setuptools to 0.9.8 solve this error, but it comes out other errors which need upgrade setuptools...