Can anyone successfully run this project, please tell me your versions, thx

[itsrealkk]

Can anyone successfully run this project, please tell me your versions, thx

[XinZhangRadar]

python 3.6 pytorch 1.6 cuda 10.2 conda install pytorch==1.6 torchvision torchaudio cudatoolkit=10.2 -c pytorch

detectron2 0.2.1

python -m pip install detectron2==0.2.1 -f 
 https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.6/index.html

apex : note that gcc >5

[itsrealkk]

python 3.6 pytorch 1.6 cuda 10.2 conda install pytorch==1.6 torchvision torchaudio cudatoolkit=10.2 -c pytorch

detectron2 0.2.1

python -m pip install detectron2==0.2.1 -f 
 https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.6/index.html

apex : note that gcc >5

thx

[Gaodzlearn]

python 3.6 pytorch 1.6 cuda 10.2 conda install pytorch==1.6 torchvision torchaudio cudatoolkit=10.2 -c pytorch

detectron2 0.2.1

python -m pip install detectron2==0.2.1 -f 
 https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.6/index.html

apex : note that gcc >5

Can you use this configuration (MODEL.QUERY.QUERY_INFER=True) for your environment? I use this configuration to run visdrone_inference.py, an error will be reported in the sparse convolution.

[08/01 17:20:06 fvcore.common.checkpoint]: [Checkpointer] Loading from /data3/ysl/quarydet_code/QueryDet-PyTorch/runs/exp1/model_0034999.pth ... [08/01 17:20:08 d2.data.common]: Serializing 98 elements to byte tensors and concatenating them all ... [08/01 17:20:08 d2.data.common]: Serialized dataset takes 0.02 MiB [08/01 17:20:12 d2.evaluation.evaluator]: Start inference on 98 images SPCONV_DEBUG_SAVE_PATH not found, you can specify SPCONV_DEBUG_SAVE_PATH as debug data save path to save debug data which can be attached in a issue. [Exception|implicit_gemm]feat=torch.Size([148, 256]),w=torch.Size([3, 3, 256, 256]),pair=torch.Size([9, 148]),act=148,issubm=True,istrain=True Traceback (most recent call last): File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/contextlib.py", line 131, in exit self.gen.throw(type, value, traceback) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/detectron2/evaluation/evaluator.py", line 195, in inference_context yield File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/detectron2/evaluation/evaluator.py", line 141, in inference_on_dataset outputs = model(inputs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(input, **kwargs) File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/detector.py", line 166, in forward return self.test(batched_inputs) File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/detector.py", line 209, in test results, total_time = self.test_forward(images) # normal test File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/detector.py", line 254, in test_forward det_cls_query, det_bbox_query, query_anchors = self.qInfer.run_qinfer(params, features_key, features_value, anchors_value) File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/qinfer.py", line 166, in run_qinfer cls_result = self._run_spconvs(x, self.cls_spconv).view(-1, self.anchor_numself.num_classes)[inds] File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/qinfer.py", line 131, in _run_spconvs y = filters(x) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/modules.py", line 137, in forward input = module(input) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/conv.py", line 441, in forward out_features = Fsp.implicit_gemm( File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/cuda/amp/autocast_mode.py", line 209, in decorate_fwd return fwd(*args, **kwargs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/functional.py", line 200, in forward raise e File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/functional.py", line 185, in forward out, mask_out, mask_width = ops.implicit_gemm(features, filters, File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/ops.py", line 1103, in implicit_gemm tune_res, _ = CONV.tune_and_cache( File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/algo.py", line 660, in tune_and_cache ConvMainUnitTest.implicit_gemm2(params) ValueError: /tmp/pip-build-env-xxm94833/overlay/lib/python3.8/site-packages/cumm/include/tensorview/check.h(32) shape_ten[i] == shape[i] assert faild. error shape [9, 148] expect [768, -1] python-BaseException

[XinZhangRadar]

python 3.6 pytorch 1.6 cuda 10.2 conda install pytorch==1.6 torchvision torchaudio cudatoolkit=10.2 -c pytorch detectron2 0.2.1

python -m pip install detectron2==0.2.1 -f 
 https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.6/index.html

apex : note that gcc >5

Can you use this configuration (MODEL.QUERY.QUERY_INFER=True) for your environment? I use this configuration to run visdrone_inference.py, an error will be reported in the sparse convolution.

[08/01 17:20:06 fvcore.common.checkpoint]: [Checkpointer] Loading from /data3/ysl/quarydet_code/QueryDet-PyTorch/runs/exp1/model_0034999.pth ... [08/01 17:20:08 d2.data.common]: Serializing 98 elements to byte tensors and concatenating them all ... [08/01 17:20:08 d2.data.common]: Serialized dataset takes 0.02 MiB [08/01 17:20:12 d2.evaluation.evaluator]: Start inference on 98 images SPCONV_DEBUG_SAVE_PATH not found, you can specify SPCONV_DEBUG_SAVE_PATH as debug data save path to save debug data which can be attached in a issue. [Exception|implicit_gemm]feat=torch.Size([148, 256]),w=torch.Size([3, 3, 256, 256]),pair=torch.Size([9, 148]),act=148,issubm=True,istrain=True Traceback (most recent call last): File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/contextlib.py", line 131, in exit self.gen.throw(type, value, traceback) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/detectron2/evaluation/evaluator.py", line 195, in inference_context yield File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/detectron2/evaluation/evaluator.py", line 141, in inference_on_dataset outputs = model(inputs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(_input, **kwargs) File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/detector.py", line 166, in forward return self.test(batched_inputs) File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/detector.py", line 209, in test results, total_time = self.test_forward(images) # normal test File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/detector.py", line 254, in test_forward det_cls_query, det_bbox_query, query_anchors = self.qInfer.run_qinfer(params, features_key, features_value, anchors_value) File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/qinfer.py", line 166, in run_qinfer cls_result = self._run_spconvs(x, self.cls_spconv).view(-1, self.anchor_num_self.num_classes)[inds] File "/data3/ysl/quarydet_code/QueryDet-PyTorch/models/querydet/qinfer.py", line 131, in _run_spconvs y = filters(x) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/modules.py", line 137, in forward input = module(input) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/conv.py", line 441, in forward out_features = Fsp.implicit_gemm( File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/torch/cuda/amp/autocast_mode.py", line 209, in decorate_fwd return fwd(*args, **kwargs) File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/functional.py", line 200, in forward raise e File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/functional.py", line 185, in forward out, mask_out, mask_width = ops.implicit_gemm(features, filters, File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/pytorch/ops.py", line 1103, in implicit_gemm tune_res, _ = CONV.tune_and_cache( File "/home/ysl/anaconda3/envs/quarydet/lib/python3.8/site-packages/spconv/algo.py", line 660, in tune_and_cache ConvMainUnitTest.implicit_gemm2(params) ValueError: /tmp/pip-build-env-xxm94833/overlay/lib/python3.8/site-packages/cumm/include/tensorview/check.h(32) shape_ten[i] == shape[i] assert faild. error shape [9, 148] expect [768, -1] python-BaseException

https://github.com/ChenhongyiYang/QueryDet-PyTorch/issues/42#issuecomment-1200774736

[Alasile]

python 3.6 pytorch 1.6 cuda 10.2 conda install pytorch==1.6 torchvision torchaudio cudatoolkit=10.2 -c pytorch

detectron2 0.2.1

python -m pip install detectron2==0.2.1 -f 
 https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.6/index.html

apex : note that gcc >5

can you share something about apex,I find when i install it, it will cause many errors.###

[ChenhongyiYang]

Hi, we have recently updated the whole repository to support newer versions of PyTorch, Detectron2, and Spconv. Now, you can set up your environment by running the sample setup script in ReadMe.