"urllib.error.HTTPError: HTTP Error 403: Forbidden" during training

[123dddd]

Hi, thanks for the great repo! I used the docker to train the HTC model on Cityperson dataset, but the following error appeared:

2022-01-10 20:14:25,077 - INFO - Distributed training: False 2022-01-10 20:14:27,061 - INFO - load model from: open-mmlab://resnext101_64x4d Downloading: "https://s3.ap-northeast-2.amazonaws.com/open-mmlab/pretrain/third_party/resnext101_64x4d-ee2c6f71.pth" to /root/.cache/torch/checkpoints/resnext101_64x4d-ee2c6f71.pth Traceback (most recent call last): File "tools/train.py", line 98, in main() File "tools/train.py", line 76, in main cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg) File "/root/Pedestron/mmdet/models/builder.py", line 43, in build_detector return build(cfg, DETECTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg)) File "/root/Pedestron/mmdet/models/builder.py", line 15, in build return build_from_cfg(cfg, registry, default_args) File "/root/Pedestron/mmdet/utils/registry.py", line 74, in build_from_cfg return obj_type(args) File "/root/Pedestron/mmdet/models/detectors/htc.py", line 23, in init super(HybridTaskCascade, self).init(num_stages, backbone, kwargs) File "/root/Pedestron/mmdet/models/detectors/cascade_rcnn.py", line 86, in init self.init_weights(pretrained=pretrained) File "/root/Pedestron/mmdet/models/detectors/cascade_rcnn.py", line 94, in init_weights self.backbone.init_weights(pretrained=pretrained) File "/root/Pedestron/mmdet/models/backbones/resnet.py", line 484, in init_weights load_checkpoint(self, pretrained, strict=False, logger=logger) File "/opt/conda/lib/python3.6/site-packages/mmcv/runner/checkpoint.py", line 140, in load_checkpoint checkpoint = load_url_dist(open_mmlab_model_urls[model_name]) File "/opt/conda/lib/python3.6/site-packages/mmcv/runner/checkpoint.py", line 99, in load_url_dist checkpoint = model_zoo.load_url(url) File "/opt/conda/lib/python3.6/site-packages/torch/hub.py", line 485, in load_state_dict_from_url download_url_to_file(url, cached_file, hash_prefix, progress=progress) File "/opt/conda/lib/python3.6/site-packages/torch/hub.py", line 384, in download_url_to_file u = urlopen(url) File "/opt/conda/lib/python3.6/urllib/request.py", line 223, in urlopen return opener.open(url, data, timeout) File "/opt/conda/lib/python3.6/urllib/request.py", line 532, in open response = meth(req, response) File "/opt/conda/lib/python3.6/urllib/request.py", line 642, in http_response 'http', request, response, code, msg, hdrs) File "/opt/conda/lib/python3.6/urllib/request.py", line 570, in error return self._call_chain(args) File "/opt/conda/lib/python3.6/urllib/request.py", line 504, in _call_chain result = func(args) File "/opt/conda/lib/python3.6/urllib/request.py", line 650, in http_error_default raise HTTPError(req.full_url, code, msg, hdrs, fp) urllib.error.HTTPError: HTTP Error 403: Forbidden

It seems that I cannot scrape this pre-trained ResNetX101 model from the web. Any suggestion will be appreciated! Thanks.