jpy.cas

Hi @leoxiaobin , thanks for your great work: HRNet. As readme files mentioned: pose_hrnet_w48* means using additional data from AI challenger for training. As we all know, AI Challenge has...

ONNX conversion issue?

4

As I want to convert pytorch model to onnx. Then convert onnx -> coreml/mnn. There are some common issues when converting. So it's a place to share the experience regarding...

How to solve multiple polygons(holes) in one instance segmentation?

6

As describe in question, I met one issue. For example, for a person's instance segmentation, there might be more than 1 polygon in the mask. some holes appeared in the...

IndexError: list assignment index out of range

2

## 🐞Describe the bug convert onnx to coreml for yolact(with slice, topK ops) ## Trace 345/361: Converting Node Type Gather 346/361: Converting Node Type Gather 347/361: Converting Node Type Concat...

TypeError: dist must be a Distribution instance

6

**pytorch:1.2.0, torchvision:0.4.0** When I excute the comand: **python build.py install** as errors occured(create_extension is deprecated), so I edit the code as below: # from torch.utils.ffi import create_extension? from torch.utils.cpp_extension import...

ImportError: cannot import name 'deform_conv_cuda'

1

When I run: python video.py, errors occured. **ImportError: cannot import name 'deform_conv_cuda'** Someone suggest reinstall pytorch==1.0.1, I try but it dosen't work. @lxy5513 Do you have any suggestion? error displays...

onnx2coreml conversion issue

3

Hi @Ma-Dan , a few conversion question confused me. pls share your experience. **1.Run yolcat code with ONNX and CoreML converter to convert to ONNX model (WITHOUT priors layer).** Q:...

TypeError: unsupported operand type(s) for |: 'type' and 'NoneType'

5

@wilson1yan It didn't work. More samples are needed including language and vision version. ./scripts/run_vision_chat.sh Traceback (most recent call last): File "/home/jiapeiyang/anaconda3/envs/nlp/lib/python3.9/runpy.py", line 197, in _run_module_as_main return _run_code(code, main_globals, None, File...

How to set the input length parameter to support long context window e.g. 256k inputs?

1

please provide an example. both vision and language are needed, thanks @wilson1yan

when I run Tengine-app with my own caffe model, it is ok for most of the time. But it will crash unexpectedlty. The memory shows no problem. Errors might happen...