[QUESTION] How to use pre trained model and pth?

D-X-Y / landmark-detection

Four landmark detection algorithms, implemented in PyTorch.

https://xuanyidong.com/assets/projects/TPAMI-2020-SRT.html

MIT License

925 stars 180 forks source link

[QUESTION] How to use pre trained model and pth? #63

Closed sevaraMS closed 4 years ago

sevaraMS commented 4 years ago

I want to just see output result of 68 predicted points, When I tried visualize the 68 points, using pre trained eval-epoch-049-050-02-03.pth it is give me mistake. FileNotFoundError: [Errno 2] No such file or directory: '/home/dxy/datasets/landmark-datasets/300W/helen/testset/3243018729_1.jpg'

D-X-Y commented 4 years ago

The pre-trained model is trained on my machine, where the data path is at "/home/dxy/datasets/landmark-datasets/" and it will be saved. There are two options,

Using our pre-trained model to predict on your own images.
Replace the file path to the path on your machine. (You need to modify the path at here: https://github.com/D-X-Y/landmark-detection/blob/master/SAN/lib/san_vision/evaluation_util.py#L36).

sevaraMS commented 4 years ago

THANK YOU