HiddenMarkovModel

> We will detect the layers where the in_chan and out_chan are not pruned peer-to-peer, and disable the pruning on these layers. I'm checking the detection. I use 'exclude' to...

> There's a bug in the conflicts detection when the first layer with depthwise separable is set to be pruned. But I think first layer with depthwise separable should not...

> Could you please offer a runnable code that I can test it Code Repository: [https://github.com/HiddenMarkovModel/LightWeightOpenposePruning](url) You should build folder "checkpoints" in root, download model from [https://drive.google.com/file/d/11h0tkTqpX76ikv4HotHgHb-eDDbL5NQj/view](url) and then restore...

> reproduced the bug. need some time to fix it Please replay after you fixed it~~

@yangapku 您好, 你可以公布一下Chinese CLIP结合Stabel Diffusion的代码吗? 我在结合的时候遇到了很多问题

``` from PIL import Image from transformers import ChineseCLIPProcessor, ChineseCLIPModel from diffusers import StableDiffusionXLPipeline import torch from pathlib import Path device = "cuda" sdxl_model_path = "stable-diffusion-xl-base-1.0" clip_model_root = "chinese-clip-vit-large-patch14" clip_text_model...

mmpose is a shit

Use script: mmpose/demo/topdown_demo_with_mmdet.py. Set param: ``` args.show = False args.device = "cuda:4" args.det_config = 'path/to/object_detector_config' args.det_checkpoint = 'path/to/object_detector_checkpoint' args.pose_config = 'mmpose/configs/wholebody_2d_keypoint/rtmpose/ubody/rtmpose-l_8xb32-270e_coco-ubody-wholebody-384x288.py' args.pose_checkpoint = 'path/to/model/dw-ll_ucoco_384.pth' args.input = 'video.mp4' args.output_root = 'result'...