xddlj

Results 12 issues of xddlj

Can you share the Pascal pretrained model-----ascal_base_trained.pth?thanks!

![aaa](https://user-images.githubusercontent.com/13918922/126988043-ec6a8793-eb73-46b4-9eb7-26a40ba0636a.png)

How can I achieve the human parsing task,Do you have any instructions?

Can you provide a simply script to get the visualization result?

# Expected Behavior Jim.read() to read the file lenna.write('lena-small-bw.jpg') to write a file to the local folder. # Current Behavior Jim.read() works fine. lenna.write('lena-small-bw.jpg') throws an error # Failure Information...

help wanted
bug
good first issue

bash scripts/evaluate_atr_kwf1.sh the content of evaluate_atr_kwf1.sh: export PYTHONPATH="${PYTHONPATH}:$(pwd)" python ./exp/train.py \ --batch 2 \ --gpus 1 \ --resume_model ./data/pretrained_model/atr_kwf1.pth \ --resume_epoch 39 \ --lr 0.001 \ --numworker 6 \ --testInterval...

RuntimeError: Exporting the operator deform_conv2d to opset version 11 is not supported. Please open a bug to request ONNX export support for the missing operator

I would like to use the pretrained weights to initialize the model, then Fine-Tuning on my custom dataset with same keypoints. I assume I would to do the following: 1....

get the LitePose-Auto-L model coco dataset (map 62.5) is through Normal Training or Super-net Training? To train network with search-L architecture with coco dataset, I use the following script: python...

can you provide a demo example for inference?