ssunguotu

> > I do not have this error using the current code on my end. > > When I use the weight provided by your interal prod_weights "VOC2Clipart.pth" , the...

I found there has something wrong in `adaptive_teacher/adapteacher/checkpoint/detection_checkpoint.py` ，and I fixed it. ``` class DetectionTSCheckpointer(DetectionCheckpointer): def _load_model(self, checkpoint): if checkpoint.get("__author__", None) == "Caffe2": # pretrained model weight: only update student...

> Does this [link](https://drive.google.com/drive/folders/1bcWh3XuQzdct4-UPTrIX-lvs47OiLaOM?usp=sharing) work? It seems the link is not working again... Could you kindly provide a new link?

我也对这个代码进行了复现，这套代码是基于这个库的：`https://github.com/jwyang/faster-rcnn.pytorch` 具体来说，我使用的环境是CUDA9.1，Pytorch0.4.0，python3.6，gcc4.8. 需要用pip/conda安装的库有： ```python cython cffi opencv-python scipy==1.2.1 msgpack easydict matplotlib pyyaml tensorboardX torchvision==0.2.2 ``` 希望能帮到你~