tsly123

Hi, Thank you for sharing your work. I there anyway to convert the 3D landmark dataset to 2D 68 point landmark (without occluded) as shown in the **Detect 2D facial...

StarGAN-JTN training CelebA and RaFD facial expression synthesis

5

Hi, Thank you for sharing your work @yunjey I am training StarGAN-JNT CelebA and RaFD for facial expression synthesis on CelebA. The training hasn't done yet (110k/200k iters) but the...

Inference

1

Hi, Thank you for your work. As mention is the title, is there any guide to do the inference? Thank you, tsly

Hi @cydonia999, First, thank you for your work. I try to detect the face with resized image (`512x512x3`). I added the `cv2.resize` function to your code but the result was...

Hi @Tsingularity @KMnP , Thank you for the great work. In the [get_df](https://github.com/KMnP/vpt/blob/main/src/utils/vis_utils.py#L158) function which summarizes the results. Line [179](https://github.com/KMnP/vpt/blob/main/src/utils/vis_utils.py#L179C45-L179C53) ``` metric_b = "val_top1" best_epoch = np.argmax(eval_results[metric_b]) ``` Here, everything...

Hi, Thank you for the greate work. This repo (VPT) provides the link to download the MoCo-v3 pretrained weights, named as `mocov3_linear-vit-b-300ep.pth.tar`. According to the [MoCo-v3 github page](https://github.com/facebookresearch/moco-v3/blob/main/CONFIG.md) (at the...

Hi, Thank you for sharing your work. Can you release conditional/unconditional checkpoints for generating images on other datasets, CIFAR10/100? Thank you.

Hi Choi, Firstly, thank you for your work on collecting recent paper on action recognition. Second, I have a question and I hope we can discuss it here. In almost...