dbolya
commented
4 years ago Your pytorch version is not high enough (you have version 1.0.0 judging by that error, while 1.0.1 is the minimum version required). Did you install the requirements through the environment.yml or is this your own environment?
You should be able to fix this by simply updating Pytorch.
When I try to use following command on anaconda prompt, it does not work well. What's the problem?
I installed python 3.7.3, CUDA 10.2, cuDNN 7.3.0 (to suit my environment), anaconda. Also git Bash to download COCO dataset.
I followed installation on this website correctly (I guess), to "sh data/scripts/COCO_test.sh" sentence. (There was no error)
However if I try to execute eval.py, there is error :
==========================================================
(base) C:\Users\Ai\yolactNew\yolact>python eval.py --trained_model=weights/yolact_base_54_800000.pth Config not specified. Parsed yolact_base_config from the file name.
loading annotations into memory... Done (t=1.11s) creating index... index created! Loading model... Done.
Traceback (most recent call last): File "eval.py", line 1105, in
evaluate(net, dataset)
File "eval.py", line 949, in evaluate
preds = net(batch)
File "C:\Users\Ai\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "C:\Users\Ai\yolactNew\yolact\yolact.py", line 676, in forward
return self.detect(pred_outs, self)
File "C:\Users\Ai\yolactNew\yolact\layers\functions\detection.py", line 71, in call
result = self.detect(batch_idx, conf_preds, decoded_boxes, mask_data, inst_data)
File "C:\Users\Ai\yolactNew\yolact\layers\functions\detection.py", line 101, in detect
boxes, masks, classes, scores = self.fast_nms(boxes, masks, scores, self.nms_thresh, self.top_k)
File "C:\Users\Ai\yolactNew\yolact\layers\functions\detection.py", line 149, in fastnms
iou.triu(diagonal=1)
RuntimeError: invalid argument 1: expected a matrix at c:\a\w\1\s\tmp_conda_3.7_061434\conda\conda-bld\pytorch_1544163540495\work\aten\src\thc\generic/THCTensorMathPairwise.cu:203