Ming-Hsuan-Tu
Ming-Hsuan-Tu
Do you know where is the source of VGG2_FP? what I can find is the aligned vgg2_fp, not original vgg2_fp.
Hi Did you reproduce megaface result on pytorch? thank you
在 pc 上跑 cpu 時間不快，直接跑範例圖(./image_04.jpg) 大概 0.1s 換成 opencl 反而會 crash ``` reshape not support dimensions == 3 The Creator Don't support type 73, BoxPredictor_0/Reshape_1 reshape not support dimensions ==...
Hi, to normalize loss, you divide the loss by the total count of anchors, but the paper suggest to divide only the positive anchors. Why did you do that? thanks
hi, Do you have any ideas about integrating javacomplete and its dependency nailgun work together. I have installed nailgun and start its server, but javacomplete still not work. Since there...
Hi, I have trained a face detector based on ohem loss (https://github.com/biubug6/Pytorch_Retinaface/blob/master/layers/modules/multibox_loss.py#L103) and now I have replaced the regression loss and classification loss with ghm-c and ghm-r. However, it seems...
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...
Trying to use ``` python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768 ``` I set n_iter to 1000 and...
Hi, I am wondering if there is any way to associate the accuracies between models of the artifacts? Like we have model v0, v1, v2, each of them have the...
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...