00_align_face.sh errors out due to hardcoded paths and missing weights/.pth(s) about celebbasis HOT 5 CLOSED

You need to add the weights files from your screenshot somewhere and fix the paths:

• "epoch59.pth" https://drive.google.com/file/d/1Jb97z5Z5ca61-6W2RDOK0e2w_RlbeWgS/view?usp=drive_link
• "FaceBoxesV2.pth" https://github.com/jhb86253817/PIPNet/blob/master/FaceBoxesV2/weights/FaceBoxesV2.pth

from celebbasis.

We use PIPNet to align and crop the face, but missed their weight files.
You may visit PIPNet repo to download the missing weight files or using the files provided by @justindujardin .
These files can also be downloaded from our Baidu Yun Drive with extracting code ygss.
We'll fix the hardcoded file paths ASAP!

from celebbasis.

Just updating the paths to relative paths (after putting the weight files there) works:

evaluation/face_align/PIPNet/lib/tools.py line 60:

    weight_file = 'evaluation/face_align/PIPNet/weights/epoch59.pth'
    state_dict = torch.load(weight_file, map_location=device)
    net.load_state_dict(state_dict)

    detector = FaceBoxesDetector(
        "FaceBoxes",
        "evaluation/face_align/PIPNet/weights/FaceBoxesV2.pth",
        use_gpu=True,
        device="cuda:0",
    )

from celebbasis.

This entire section of code is also full of hardcoded paths:
https://github.com/ygtxr1997/CelebBasis/blob/main/scripts/stable_txt2img.py#L272

from celebbasis.

Just updating the paths to relative paths (after putting the weight files there) works:

evaluation/face_align/PIPNet/lib/tools.py line 60:

    weight_file = 'evaluation/face_align/PIPNet/weights/epoch59.pth'
    state_dict = torch.load(weight_file, map_location=device)
    net.load_state_dict(state_dict)

    detector = FaceBoxesDetector(
        "FaceBoxes",
        "evaluation/face_align/PIPNet/weights/FaceBoxesV2.pth",
        use_gpu=True,
        device="cuda:0",
    )

1. Code updated, 82fdc0e.

This entire section of code is also full of hardcoded paths: https://github.com/ygtxr1997/CelebBasis/blob/main/scripts/stable_txt2img.py#L272

2. For stable_txt2img.py#L272, these hardcoded paths are not used under the default setting. We consider removing these codes or adding the relevant testing options.

from celebbasis.