Feywell
Feywell
Thanks for you great work to reimplement hififace! I find that you use the Deep3dFaceRecon model straightly in size (256, 256). But the offical code of Deep3dFaceRecon is (224, 224)....
I try to change code to use torch.ditributed. But, It will done without errors in https://github.com/ZPdesu/SEAN/blob/04c7536ff3fecd2d1a09c9ae046a1144636033a5/models/networks/normalization.py#L119. I found it will done with `torch.randn(x.shape[0], x.shape[3], x.shape[2], 1).cuda() `. It is weird.
I try to change this code to implement video object detecction. I find the test phase is slow. Then I visualize the time cost. I find nms is key reason....
I try to train a model by my own dataset. But it is interrupt. How can I resume trainging It will return a error when using resume training： > RuntimeError:...
I want to train a matting model by my own dataset. It will be used in high resolution imgs. Why is it not clear. How can I train my model...
I try to use composition loss in my training. And then, I find the merged img's color is different from image. Why the color jitter is just be used on...
If bg_num < batch_size, there is a error like title. And it will always one image, when bg_num = 1, batch_size = 1.
I want to test mAP for different IoU. But I find the params thresh of `vid_eval ` in ` dataset/imagenet_vid_eval.py` is not work. What is the IoU thresh of test...
I try to use do_python_eval() in lib/dataset/imagenet_vid.py to calculate mAP by classes. But I get a results like : > AP for airplane = 0.0047 > AP for antelope =...
There are some trouble to use OneDrive to download the pretrained model in China. Can you provide another way ( like BaiduYun or Google )to download, please! Thank you!