JialeCao001 / SipMask

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
https://arxiv.org/pdf/2007.14772.pdf
MIT License
334 stars 54 forks source link

forward() takes from 3 to 4 positional arguments but 5 were given #61

Open chyphen7 opened 2 years ago

chyphen7 commented 2 years ago

I am trying to run "python demo/fcos_demo.py", but get the following errors.

(FCOS) PS G:\DeepLearning\segmentation\SipMask\SipMask-benchmark> python demo/fcos_demo.py Traceback (most recent call last): File "G:\DeepLearning\segmentation\SipMask\SipMask-benchmark\demo\fcos_demo.py", line 109, in main() File "G:\DeepLearning\segmentation\SipMask\SipMask-benchmark\demo\fcos_demo.py", line 101, in main composite = coco_demo.run_on_opencv_image(img) File "G:\DeepLearning\segmentation\SipMask\SipMask-benchmark\demo\predictor.py", line 172, in run_on_opencv_image predictions = self.compute_prediction(image) File "G:\DeepLearning\segmentation\SipMask\SipMask-benchmark\demo\predictor.py", line 205, in compute_prediction predictions = self.model(image_list) File "D:\anaconda3\envs\FCOS\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl result = self.forward(*input, *kwargs) File "g:\deeplearning\segmentation\sipmask\sipmask-benchmark\fcos_core\modeling\detector\generalized_rcnn.py", line 51, in forward proposals, proposal_losses = self.rpn(images, features, imge_metas, targets) File "D:\anaconda3\envs\FCOS\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl result = self.forward(input, **kwargs) TypeError: forward() takes from 3 to 4 positional arguments but 5 were given

I am wondering if it is related to incompatibility of torch version or something else? Can anybody help?

Thanks, Chien