xiaoyu song

Update face2rec2.py

4

More robust for python3 user

could you explain why you are using binary cross-entropy

1

Hi, Inside the CBloss you are using binary cross-entropy, so why not using cross-entropy ? Could you explain? Thank you

Hi, thanks for publishing this code. The paper and the code are amazing. Could you please give more details about which cityspace dataset you are using? Thank you.

Hi, could you provide the cleaned 112 version MS-Celeb-1M and the list file

2

Hi, could you provide the cleaned cropped MS-Celeb-1M training data and the list file. Thank you

Hi, I tried to reproduce the result. And in the submission code. There is: ``` `from face_utils import norm_crop, FaceDetector File "/home/song/deepfake/kaggle-dfdc/face_utils.py", line 8, in from layers.functions.prior_box import PriorBox File...

Could you give more details of how the imdb-wiki rec files are preprocessed.

in train_NR.py line 301 `cross_entropy = cross_entropy / args.batch_size/2` could you explain why the loss should be divided by the batch size and then multiply by 2? thank you

target size

1

Hi, ptrblck, I don't know why your target tensor the final dimension is a tuple. could you explain y = torch.randint(0, nb_classes, (1, 96, 96))

Update unet_demo.py

1

in the unet paper, there are 4 encoders. 4 decoders.

``` --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in 1 inputs = torch.randn(1, 3, 222, 222).to(device) 2 print(inputs.dtype) ----> 3 outputs = unet(inputs) 4 print(outputs.shape) 5 print(outputs.dtype) ~/miniconda3/envs/deep_mol/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self,...