Zhuofan Zong

icon company The Chinese University of Hong Kong icon location Hong Kong icon location PhD student at MMLab, CUHK

Results 111 comments of Zhuofan Zong

Different outputs of the official LLaMA repo and transformers' implementation

I met the same problem.

pytorch to onnx

I have modified the `onnx_export` function, you can try it again

pytorch to onnx

@xueyingliu, @chenzx2, @jielanZhang, Hi, I am sorry that there are some unsolved torch2onnx issues. Our repo is implemented using an older version of mmdet v2.25, which no longer maintains the...

pytorch to onnx

@MarouaneMja Hi, I find this PR (https://github.com/open-mmlab/mmdetection/pull/10910) of mmdet v3.x supports onnx export and hope this can help you.

pytorch to onnx

@Mayyyybe The inference architecture of Co-DINO is the same as DINO. And MMdeploy supports the model export of DINO method.

pytorch to onnx

> Hi @TempleX98 , I managed to export the CO-DETR to onnx using mmdeploy as you suggested, however the SoftNonMaxSuppression is not supported by onnxruntime `failed:Fatal error: SoftNonMaxSuppression is not...

作者您好，如何启动AMP进行训练呢

目前官方mmdetection 3.2已经支持了Co-DETR算法，关于大模型训练减少显存可以参考https://github.com/open-mmlab/mmdetection/tree/main/projects/example_largemodel

Issue with Environment (mmdet)

Please try pip install -r requirements.txt

Issue with Environment (mmdet)

I have never met this issue. Maybe you can install mmdet by `pip install -v -e .` to see if it works.

freeze most of the layers and train head

I have yet to explore this configuration. Perhaps you can perform this experiment using your custom dataset to benchmark this setting.