joslefaure / hit Goto Github PK

Thank you for the wonderful work. I have read the paper and have some questions: How does your framework determine the start and end frame of an action in a video? Is a linking algorithm adopted to link per-frame detections together?

Thanks a lot for your work.
First, I ran

but the follow error occured:

So, I tried to install hit as you recommend：

but it went wrong，Could you tell me how to solve this problem？

`(hit) root@autodl-container-704e11bd52-4fa8bbcd:~/HIT-master# TORCH_CUDA_ARCH_LIST="8.0" python setup.py install
running install
/root/miniconda3/envs/hit/lib/python3.7/site-packages/setuptools/command/install.py:37: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
setuptools.SetuptoolsDeprecationWarning,
/root/miniconda3/envs/hit/lib/python3.7/site-packages/setuptools/command/easy_install.py:147: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
EasyInstallDeprecationWarning,
running bdist_egg
running egg_info
writing hit.egg-info/PKG-INFO
writing dependency_links to hit.egg-info/dependency_links.txt
writing requirements to hit.egg-info/requires.txt
writing top-level names to hit.egg-info/top_level.txt
reading manifest file 'hit.egg-info/SOURCES.txt'
writing manifest file 'hit.egg-info/SOURCES.txt'
installing library code to build/bdist.linux-x86_64/egg
running install_lib
running build_py
running build_ext
creating build/bdist.linux-x86_64/egg
creating build/bdist.linux-x86_64/egg/detector
copying build/lib.linux-x86_64-cpython-37/detector/apis.py -> build/bdist.linux-x86_64/egg/detector
copying build/lib.linux-x86_64-cpython-37/detector/tracker_api.py -> build/bdist.linux-x86_64/egg/detector
copying build/lib.linux-x86_64-cpython-37/detector/tracker_cfg.py -> build/bdist.linux-x86_64/egg/detector
copying build/lib.linux-x86_64-cpython-37/detector/yolo_api.py -> build/bdist.linux-x86_64/egg/detector
copying build/lib.linux-x86_64-cpython-37/detector/yolo_cfg.py -> build/bdist.linux-x86_64/egg/detector
copying build/lib.linux-x86_64-cpython-37/detector/init.py -> build/bdist.linux-x86_64/egg/detector
creating build/bdist.linux-x86_64/egg/detector/nms
copying build/lib.linux-x86_64-cpython-37/detector/nms/nms_wrapper.py -> build/bdist.linux-x86_64/egg/detector/nms
copying build/lib.linux-x86_64-cpython-37/detector/nms/init.py -> build/bdist.linux-x86_64/egg/detector/nms
copying build/lib.linux-x86_64-cpython-37/detector/nms/soft_nms_cpu.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg/detector/nms
copying build/lib.linux-x86_64-cpython-37/detector/nms/nms_cpu.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg/detector/nms
copying build/lib.linux-x86_64-cpython-37/detector/nms/nms_cuda.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg/detector/nms
creating build/bdist.linux-x86_64/egg/detector/tracker
copying build/lib.linux-x86_64-cpython-37/detector/tracker/models.py -> build/bdist.linux-x86_64/egg/detector/tracker
copying build/lib.linux-x86_64-cpython-37/detector/tracker/preprocess.py -> build/bdist.linux-x86_64/egg/detector/tracker
copying build/lib.linux-x86_64-cpython-37/detector/tracker/init.py -> build/bdist.linux-x86_64/egg/detector/tracker
creating build/bdist.linux-x86_64/egg/detector/tracker/tracker
copying build/lib.linux-x86_64-cpython-37/detector/tracker/tracker/basetrack.py -> build/bdist.linux-x86_64/egg/detector/tracker/tracker
copying build/lib.linux-x86_64-cpython-37/detector/tracker/tracker/matching.py -> build/bdist.linux-x86_64/egg/detector/tracker/tracker
copying build/lib.linux-x86_64-cpython-37/detector/tracker/tracker/multitracker.py -> build/bdist.linux-x86_64/egg/detector/tracker/tracker
copying build/lib.linux-x86_64-cpython-37/detector/tracker/tracker/init.py -> build/bdist.linux-x86_64/egg/detector/tracker/tracker
creating build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/datasets.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/evaluation.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/io.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/kalman_filter.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/log.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/nms.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/parse_config.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/timer.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/utils.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/visualization.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
copying build/lib.linux-x86_64-cpython-37/detector/tracker/utils/init.py -> build/bdist.linux-x86_64/egg/detector/tracker/utils
creating build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/bbox.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/cam_demo.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/darknet.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/detect.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/preprocess.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/util.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/video_demo.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/video_demo_half.py -> build/bdist.linux-x86_64/egg/detector/yolo
copying build/lib.linux-x86_64-cpython-37/detector/yolo/init.py -> build/bdist.linux-x86_64/egg/detector/yolo
creating build/bdist.linux-x86_64/egg/hit
copying build/lib.linux-x86_64-cpython-37/hit/init.py -> build/bdist.linux-x86_64/egg/hit
creating build/bdist.linux-x86_64/egg/hit/config
copying build/lib.linux-x86_64-cpython-37/hit/config/defaults.py -> build/bdist.linux-x86_64/egg/hit/config
copying build/lib.linux-x86_64-cpython-37/hit/config/paths_catalog.py -> build/bdist.linux-x86_64/egg/hit/config
copying build/lib.linux-x86_64-cpython-37/hit/config/init.py -> build/bdist.linux-x86_64/egg/hit/config
creating build/bdist.linux-x86_64/egg/hit/dataset
copying build/lib.linux-x86_64-cpython-37/hit/dataset/build.py -> build/bdist.linux-x86_64/egg/hit/dataset
copying build/lib.linux-x86_64-cpython-37/hit/dataset/collate_batch.py -> build/bdist.linux-x86_64/egg/hit/dataset
copying build/lib.linux-x86_64-cpython-37/hit/dataset/init.py -> build/bdist.linux-x86_64/egg/hit/dataset
creating build/bdist.linux-x86_64/egg/hit/dataset/datasets
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/concat_dataset.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/iou_calculator.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/jhmdb.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/init.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets
creating build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/init.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation
creating build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/jhmdb_eval.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/init.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb
creating build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/label_map_util.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/metrics.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_list.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_list_ops.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_mask_list.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_mask_list_ops.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_ops.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_mask_ops.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/object_detection_evaluation.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/per_image_evaluation.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/standard_fields.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
copying build/lib.linux-x86_64-cpython-37/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/init.py -> build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation
creating build/bdist.linux-x86_64/egg/hit/dataset/samplers
copying build/lib.linux-x86_64-cpython-37/hit/dataset/samplers/distributed.py -> build/bdist.linux-x86_64/egg/hit/dataset/samplers
copying build/lib.linux-x86_64-cpython-37/hit/dataset/samplers/grouped_batch_sampler.py -> build/bdist.linux-x86_64/egg/hit/dataset/samplers
copying build/lib.linux-x86_64-cpython-37/hit/dataset/samplers/iteration_based_batch_sampler.py -> build/bdist.linux-x86_64/egg/hit/dataset/samplers
copying build/lib.linux-x86_64-cpython-37/hit/dataset/samplers/init.py -> build/bdist.linux-x86_64/egg/hit/dataset/samplers
creating build/bdist.linux-x86_64/egg/hit/dataset/transforms
copying build/lib.linux-x86_64-cpython-37/hit/dataset/transforms/build.py -> build/bdist.linux-x86_64/egg/hit/dataset/transforms
copying build/lib.linux-x86_64-cpython-37/hit/dataset/transforms/object_transforms.py -> build/bdist.linux-x86_64/egg/hit/dataset/transforms
copying build/lib.linux-x86_64-cpython-37/hit/dataset/transforms/video_transforms.py -> build/bdist.linux-x86_64/egg/hit/dataset/transforms
copying build/lib.linux-x86_64-cpython-37/hit/dataset/transforms/init.py -> build/bdist.linux-x86_64/egg/hit/dataset/transforms
creating build/bdist.linux-x86_64/egg/hit/engine
copying build/lib.linux-x86_64-cpython-37/hit/engine/inference.py -> build/bdist.linux-x86_64/egg/hit/engine
copying build/lib.linux-x86_64-cpython-37/hit/engine/trainer.py -> build/bdist.linux-x86_64/egg/hit/engine
copying build/lib.linux-x86_64-cpython-37/hit/engine/init.py -> build/bdist.linux-x86_64/egg/hit/engine
creating build/bdist.linux-x86_64/egg/hit/layers
copying build/lib.linux-x86_64-cpython-37/hit/layers/batch_norm.py -> build/bdist.linux-x86_64/egg/hit/layers
copying build/lib.linux-x86_64-cpython-37/hit/layers/roi_align_3d.py -> build/bdist.linux-x86_64/egg/hit/layers
copying build/lib.linux-x86_64-cpython-37/hit/layers/roi_pool_3d.py -> build/bdist.linux-x86_64/egg/hit/layers
copying build/lib.linux-x86_64-cpython-37/hit/layers/sigmoid_focal_loss.py -> build/bdist.linux-x86_64/egg/hit/layers
copying build/lib.linux-x86_64-cpython-37/hit/layers/softmax_focal_loss.py -> build/bdist.linux-x86_64/egg/hit/layers
copying build/lib.linux-x86_64-cpython-37/hit/layers/init.py -> build/bdist.linux-x86_64/egg/hit/layers
creating build/bdist.linux-x86_64/egg/hit/modeling
copying build/lib.linux-x86_64-cpython-37/hit/modeling/common_blocks.py -> build/bdist.linux-x86_64/egg/hit/modeling
copying build/lib.linux-x86_64-cpython-37/hit/modeling/nonlocal_block.py -> build/bdist.linux-x86_64/egg/hit/modeling
copying build/lib.linux-x86_64-cpython-37/hit/modeling/poolers.py -> build/bdist.linux-x86_64/egg/hit/modeling
copying build/lib.linux-x86_64-cpython-37/hit/modeling/registry.py -> build/bdist.linux-x86_64/egg/hit/modeling
copying build/lib.linux-x86_64-cpython-37/hit/modeling/utils.py -> build/bdist.linux-x86_64/egg/hit/modeling
copying build/lib.linux-x86_64-cpython-37/hit/modeling/init.py -> build/bdist.linux-x86_64/egg/hit/modeling
creating build/bdist.linux-x86_64/egg/hit/modeling/backbone
copying build/lib.linux-x86_64-cpython-37/hit/modeling/backbone/backbone.py -> build/bdist.linux-x86_64/egg/hit/modeling/backbone
copying build/lib.linux-x86_64-cpython-37/hit/modeling/backbone/i3d.py -> build/bdist.linux-x86_64/egg/hit/modeling/backbone
copying build/lib.linux-x86_64-cpython-37/hit/modeling/backbone/slowfast.py -> build/bdist.linux-x86_64/egg/hit/modeling/backbone
copying build/lib.linux-x86_64-cpython-37/hit/modeling/backbone/init.py -> build/bdist.linux-x86_64/egg/hit/modeling/backbone
creating build/bdist.linux-x86_64/egg/hit/modeling/detector
copying build/lib.linux-x86_64-cpython-37/hit/modeling/detector/action_detector.py -> build/bdist.linux-x86_64/egg/hit/modeling/detector
copying build/lib.linux-x86_64-cpython-37/hit/modeling/detector/init.py -> build/bdist.linux-x86_64/egg/hit/modeling/detector
creating build/bdist.linux-x86_64/egg/hit/modeling/roi_heads
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/roi_heads_3d.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/init.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads
creating build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/action_head.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/hit_structure.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/inference.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/loss.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/metric.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/pose_transformer.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/roi_action_feature_extractor.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/roi_action_predictors.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
copying build/lib.linux-x86_64-cpython-37/hit/modeling/roi_heads/action_head/init.py -> build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head
creating build/bdist.linux-x86_64/egg/hit/solver
copying build/lib.linux-x86_64-cpython-37/hit/solver/build.py -> build/bdist.linux-x86_64/egg/hit/solver
copying build/lib.linux-x86_64-cpython-37/hit/solver/lr_scheduler.py -> build/bdist.linux-x86_64/egg/hit/solver
copying build/lib.linux-x86_64-cpython-37/hit/solver/init.py -> build/bdist.linux-x86_64/egg/hit/solver
creating build/bdist.linux-x86_64/egg/hit/structures
copying build/lib.linux-x86_64-cpython-37/hit/structures/bounding_box.py -> build/bdist.linux-x86_64/egg/hit/structures
copying build/lib.linux-x86_64-cpython-37/hit/structures/memory_pool.py -> build/bdist.linux-x86_64/egg/hit/structures
copying build/lib.linux-x86_64-cpython-37/hit/structures/init.py -> build/bdist.linux-x86_64/egg/hit/structures
creating build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/c2_model_loading.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/checkpoint.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/comm.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/IA_helper.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/logger.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/metric_logger.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/model_serialization.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/random_seed.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/registry.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/video_decode.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/utils/init.py -> build/bdist.linux-x86_64/egg/hit/utils
copying build/lib.linux-x86_64-cpython-37/hit/_custom_cuda_ext.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg/hit
byte-compiling build/bdist.linux-x86_64/egg/detector/apis.py to apis.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker_api.py to tracker_api.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker_cfg.py to tracker_cfg.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo_api.py to yolo_api.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo_cfg.py to yolo_cfg.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/nms/nms_wrapper.py to nms_wrapper.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/nms/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/models.py to models.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/preprocess.py to preprocess.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/tracker/basetrack.py to basetrack.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/tracker/matching.py to matching.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/tracker/multitracker.py to multitracker.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/tracker/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/datasets.py to datasets.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/evaluation.py to evaluation.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/io.py to io.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/kalman_filter.py to kalman_filter.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/log.py to log.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/nms.py to nms.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/parse_config.py to parse_config.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/timer.py to timer.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/utils.py to utils.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/visualization.py to visualization.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/tracker/utils/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/bbox.py to bbox.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/cam_demo.py to cam_demo.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/darknet.py to darknet.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/detect.py to detect.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/preprocess.py to preprocess.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/util.py to util.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/video_demo.py to video_demo.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/video_demo_half.py to video_demo_half.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/yolo/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/config/defaults.py to defaults.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/config/paths_catalog.py to paths_catalog.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/config/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/build.py to build.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/collate_batch.py to collate_batch.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/concat_dataset.py to concat_dataset.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/iou_calculator.py to iou_calculator.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/jhmdb.py to jhmdb.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/jhmdb_eval.py to jhmdb_eval.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/label_map_util.py to label_map_util.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/metrics.py to metrics.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_list.py to np_box_list.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_list_ops.py to np_box_list_ops.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_mask_list.py to np_box_mask_list.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_mask_list_ops.py to np_box_mask_list_ops.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_box_ops.py to np_box_ops.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/np_mask_ops.py to np_mask_ops.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/object_detection_evaluation.py to object_detection_evaluation.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/per_image_evaluation.py to per_image_evaluation.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/standard_fields.py to standard_fields.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/datasets/evaluation/jhmdb/pascal_evaluation/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/samplers/distributed.py to distributed.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/samplers/grouped_batch_sampler.py to grouped_batch_sampler.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/samplers/iteration_based_batch_sampler.py to iteration_based_batch_sampler.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/samplers/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/transforms/build.py to build.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/transforms/object_transforms.py to object_transforms.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/transforms/video_transforms.py to video_transforms.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/dataset/transforms/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/engine/inference.py to inference.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/engine/trainer.py to trainer.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/engine/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/layers/batch_norm.py to batch_norm.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/layers/roi_align_3d.py to roi_align_3d.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/layers/roi_pool_3d.py to roi_pool_3d.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/layers/sigmoid_focal_loss.py to sigmoid_focal_loss.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/layers/softmax_focal_loss.py to softmax_focal_loss.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/layers/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/common_blocks.py to common_blocks.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/nonlocal_block.py to nonlocal_block.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/poolers.py to poolers.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/registry.py to registry.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/utils.py to utils.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/backbone/backbone.py to backbone.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/backbone/i3d.py to i3d.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/backbone/slowfast.py to slowfast.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/backbone/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/detector/action_detector.py to action_detector.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/detector/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/roi_heads_3d.py to roi_heads_3d.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/action_head.py to action_head.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/hit_structure.py to hit_structure.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/inference.py to inference.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/loss.py to loss.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/metric.py to metric.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/pose_transformer.py to pose_transformer.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/roi_action_feature_extractor.py to roi_action_feature_extractor.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/roi_action_predictors.py to roi_action_predictors.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/modeling/roi_heads/action_head/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/solver/build.py to build.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/solver/lr_scheduler.py to lr_scheduler.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/solver/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/structures/bounding_box.py to bounding_box.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/structures/memory_pool.py to memory_pool.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/structures/init.py to init.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/c2_model_loading.py to c2_model_loading.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/checkpoint.py to checkpoint.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/comm.py to comm.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/IA_helper.py to IA_helper.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/logger.py to logger.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/metric_logger.py to metric_logger.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/model_serialization.py to model_serialization.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/random_seed.py to random_seed.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/registry.py to registry.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/video_decode.py to video_decode.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/hit/utils/init.py to init.cpython-37.pyc
creating stub loader for hit/_custom_cuda_ext.cpython-37m-x86_64-linux-gnu.so
creating stub loader for detector/nms/soft_nms_cpu.cpython-37m-x86_64-linux-gnu.so
creating stub loader for detector/nms/nms_cpu.cpython-37m-x86_64-linux-gnu.so
creating stub loader for detector/nms/nms_cuda.cpython-37m-x86_64-linux-gnu.so
byte-compiling build/bdist.linux-x86_64/egg/hit/_custom_cuda_ext.py to _custom_cuda_ext.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/nms/soft_nms_cpu.py to soft_nms_cpu.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/nms/nms_cpu.py to nms_cpu.cpython-37.pyc
byte-compiling build/bdist.linux-x86_64/egg/detector/nms/nms_cuda.py to nms_cuda.cpython-37.pyc
creating build/bdist.linux-x86_64/egg/EGG-INFO
copying hit.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO
copying hit.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying hit.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying hit.egg-info/requires.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying hit.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt
zip_safe flag not set; analyzing archive contents...
detector.pycache.tracker_api.cpython-37: module references file
detector.pycache.yolo_api.cpython-37: module references file
detector.nms.pycache.nms_cpu.cpython-37: module references file
detector.nms.pycache.nms_cuda.cpython-37: module references file
detector.nms.pycache.soft_nms_cpu.cpython-37: module references file
hit.pycache._custom_cuda_ext.cpython-37: module references file
creating 'dist/hit-0.0.0-py3.7-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it
removing 'build/bdist.linux-x86_64/egg' (and everything under it)
Processing hit-0.0.0-py3.7-linux-x86_64.egg
removing '/root/miniconda3/envs/hit/lib/python3.7/site-packages/hit-0.0.0-py3.7-linux-x86_64.egg' (and everything under it)
creating /root/miniconda3/envs/hit/lib/python3.7/site-packages/hit-0.0.0-py3.7-linux-x86_64.egg
Extracting hit-0.0.0-py3.7-linux-x86_64.egg to /root/miniconda3/envs/hit/lib/python3.7/site-packages
hit 0.0.0 is already the active version in easy-install.pth

Installed /root/miniconda3/envs/hit/lib/python3.7/site-packages/hit-0.0.0-py3.7-linux-x86_64.egg
Processing dependencies for hit==0.0.0
Searching for cython-bbox
Reading https://pypi.org/simple/cython-bbox/
/root/miniconda3/envs/hit/lib/python3.7/site-packages/pkg_resources/init.py:126: PkgResourcesDeprecationWarning: is an invalid version and will not be supported in a future release
PkgResourcesDeprecationWarning,
Downloading https://files.pythonhosted.org/packages/fa/b9/fc7d60e8c3b29cc0ff24a3bb3c4b7457e10b7610fbb2893741b623487b34/cython_bbox-0.1.3.tar.gz#sha256=82e2d887534ecc10d3507489a05b11259f3baacd29eee37e6d8c97e1ffb16554
Best match: cython-bbox 0.1.3
Processing cython_bbox-0.1.3.tar.gz
Writing /tmp/easy_install-wop34sbd/cython_bbox-0.1.3/setup.cfg
Running cython_bbox-0.1.3/setup.py -q bdist_egg --dist-dir /tmp/easy_install-wop34sbd/cython_bbox-0.1.3/egg-dist-tmp-mnn08vck
Compiling src/cython_bbox.pyx because it depends on /root/miniconda3/envs/hit/lib/python3.7/site-packages/numpy/init.pxd.
[1/1] Cythonizing src/cython_bbox.pyx
/root/miniconda3/envs/hit/lib/python3.7/site-packages/Cython/Compiler/Main.py:369: FutureWarning: Cython directive 'language_level' not set, using 2 for now (Py2). This will change in a later release! File: /tmp/easy_install-wop34sbd/cython_bbox-0.1.3/src/cython_bbox.pyx
tree = Parsing.p_module(s, pxd, full_module_name)
/root/miniconda3/envs/hit/lib/python3.7/site-packages/setuptools/command/install.py:37: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
setuptools.SetuptoolsDeprecationWarning,
src/cython_bbox.c: In function ‘__pyx_pf_11cython_bbox_bbox_overlaps’:
src/cython_bbox.c:2512:22: error: incompatible types when assigning to type ‘double’ from type ‘PyObject * {aka struct _object *}’
__pyx_t_26 = __Pyx_PyObject_CallOneArg(((PyObject *)(&PyFloat_Type)), __pyx_t_1); if (unlikely(!__pyx_t_26)) __PYX_ERR(0, 49, __pyx_L1_error)
^
error: Setup script exited with error: command '/usr/bin/gcc' failed with exit code 1`

Hello, can you tell me how to use your work to train AVA data sets? How to prepare data sets and how to prepare configuration files.

Hello, when will you open the source code?

We need to inference setup the multisports model for football to find fine grain localization of football events

May I ask when the Data Preparation of ava dataset can be completed? I tried to run the code but kept failing. Thank you.

Hello, I have a very confused question about your jhmdb.py's handling of JHMDB dataset tags. The experiment is very urgent. I hope to get your reply. In jhmdb.py, you define a function: get_ Keypoints (self, idx, im_w, im_h, orig_boxes), return kpts_ Boxes, which is the largest bboxes of the original real bbox iou, right? But I see your code boxes=BoxList (boxs_sensor, (im_w, im_h), mode="xywh"). convert ("xyxy"), while orig_ Boxes=boxes. bbox,Description orig_ Boxes was originally in the xywh format and needs to be converted to the xyxy format, but in get_ During keypoints processing, idx_ to_ Keep=np.argmax (iou (orig_boxes, boxes), 1), you directly calculated the iou value and returned the index. Boxes has not been converted to xyxy. I know it is my understanding problem, but I don't know what went wrong. Can you tell me?

Hello, could you please share the processed UCF101-24 dataset?

I can't find pretrained model or JHMDB model

Could you provide the complete code about ucf-24? I want to train on this dataset, but an error always disturbed me. Thank you.

Hello, can you share the data of UCF101-24? I want to try the training of AVA dataset after UCF101-24 and JHMDB training. I hope you can share it with me. Thank you very much!

Thanks for the author's reply, I can indeed get videomAP through the instruction. I want to get the frame mAP and I see that the parameter "frameAP " exists in compute_video_map.py, so I execute the instruction "python compute_video_map.py frameAP JHMDB-GT.pkl result_jhmdb.pkl". But I get a syntax error. The following is the error message:
Traceback (most recent call last):
File "compute_video_map.py", line 427, in
frameAP(args.groundtruth, args.detections, args.thr)
File "compute_video_map.py", line 86, in frameAP
detections = alldets[alldets[:, 2] == ilabel, :]
TypeError: unhashable type: 'slice'
According to the error message TypeError: unhashable type: 'slice', the slicing operation cannot be applied to NumPy arrays.
This makes me very confused, I hope the author can give an answer,thank you very much.

For AVA dataset, How should these parameters, including MAX_PERSON, MAX_HAND and MAX_OBJECT, be set?

I ran the test script, but it did not generate a visualization of the video, it only generated a csv file and a pth file, how should I apply these results to the video?

After I run 'pip install -e .' I get the following error.
cl : Command line error D8021 : invalid numeric argument '/Wno-cpp'
error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\VC\Tools\MSVC\14.37.32822\bin\HostX86\x64\cl.exe' failed with exit code 2.
I looked at similar issues, for example one is here: cocodataset/cocoapi#51.
I tried changing extra_compile_args variable to extra_compile_args={'gcc': ['/Qstd=c99']}.
I use windows 11.

as showed in title

When I try to visualize the video, I encounter a size mismatch issue, which is also encountered in Alphaction. So how can I solve this problem?

Traceback (most recent call last):
File "demo.py", line 99, in
main()
File "demo.py", line 46, in main
checkpointer.load(cfg.MODEL.WEIGHT)
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/utils/checkpoint.py", line 61, in load
self._load_model(checkpoint, no_head)
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/utils/checkpoint.py", line 110, in _load_model
load_state_dict(self.model, checkpoint.pop("model"), no_head)
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/utils/model_serialization.py", line 83, in load_state_dict
model.load_state_dict(model_state_dict)
File "/home/user/anaconda3/envs/hit/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1406, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for ActionDetector:
size mismatch for roi_heads.action.feature_extractor.hit_structure.person_dim_reduce.weight: copying a param with shape torch.Size([1024, 2304, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1, 1]).
size mismatch for roi_heads.action.feature_extractor.hit_structure.person_key_dim_reduce.weight: copying a param with shape torch.Size([1024, 2304, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1, 1]).
size mismatch for roi_heads.action.feature_extractor.hit_structure.object_dim_reduce.weight: copying a param with shape torch.Size([1024, 2304, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1, 1]).
size mismatch for roi_heads.action.feature_extractor.hit_structure.hand_dim_reduce.weight: copying a param with shape torch.Size([1024, 2304, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1, 1]).
size mismatch for roi_heads.action.feature_extractor.fc1.weight: copying a param with shape torch.Size([1024, 2304]) from checkpoint, the shape in current model is torch.Size([1024, 256]).

Hello,

I was following the guide install.md, I'm on Windows 10, Pytorch installed for cuda11.3, GTX 1660 Ti, and here's my error when trying pip install -e .
I isolated the entire error by running only python setup.py develop

C:\Users\David Traparic\Documents\prog\HITNet\HIT-master>python setup.py develop
running develop
C:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\setuptools\command\easy_install.py:147: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
  EasyInstallDeprecationWarning,
C:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\setuptools\command\install.py:37: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
  setuptools.SetuptoolsDeprecationWarning,
running egg_info
writing hit.egg-info\PKG-INFO
writing dependency_links to hit.egg-info\dependency_links.txt
writing requirements to hit.egg-info\requires.txt
writing top-level names to hit.egg-info\top_level.txt
C:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\torch\utils\cpp_extension.py:381: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend.
  warnings.warn(msg.format('we could not find ninja.'))
reading manifest file 'hit.egg-info\SOURCES.txt'
writing manifest file 'hit.egg-info\SOURCES.txt'
running build_ext
C:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\torch\utils\cpp_extension.py:316: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
  warnings.warn(f'Error checking compiler version for {compiler}: {error}')
building 'hit._custom_cuda_ext' extension
"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.3\bin\nvcc" -c "C:\Users\David Traparic\Documents\prog\HITNet\HIT-master\hit/csrc\cuda\ROIAlign3d_cuda.cu" -o "build\temp.win-amd64-cpython-37\Release\Users\David Traparic\Documents\prog\HITNet\HIT-master\hit/csrc\cuda\ROIAlign3d_cuda.obj" "-IC:\Users\David Traparic\Documents\prog\HITNet\HIT-master\hit/csrc" "-IC:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\torch\include" "-IC:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\torch\include\torch\csrc\api\include" "-IC:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\torch\include\TH" "-IC:\Users\David Traparic\miniconda3\envs\hit\lib\site-packages\torch\include\THC" "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.3\include" "-IC:\Users\David Traparic\miniconda3\envs\hit\include" "-IC:\Users\David Traparic\miniconda3\envs\hit\Include" "-IC:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.22000.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.22000.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.22000.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.22000.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.22000.0\cppwinrt" -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -O3 -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_custom_cuda_ext -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=compute_75 -gencode=arch=compute_75,code=sm_75 --use-local-env
ROIAlign3d_cuda.cu
C:\Users\David Traparic\Documents\prog\HITNet\HIT-master\hit\csrc\cuda\ROIAlign3d_cuda.cu(277): error: no instance of function template "THCCeilDiv" matches the argument list
            argument types are: (long long, long)

C:\Users\David Traparic\Documents\prog\HITNet\HIT-master\hit\csrc\cuda\ROIAlign3d_cuda.cu(277): error: no instance of overloaded function "std::min" matches the argument list
            argument types are: (<error-type>, long)

C:\Users\David Traparic\Documents\prog\HITNet\HIT-master\hit\csrc\cuda\ROIAlign3d_cuda.cu(324): error: no instance of function template "THCCeilDiv" matches the argument list
            argument types are: (int64_t, long)

C:\Users\David Traparic\Documents\prog\HITNet\HIT-master\hit\csrc\cuda\ROIAlign3d_cuda.cu(324): error: no instance of overloaded function "std::min" matches the argument list
            argument types are: (<error-type>, long)

4 errors detected in the compilation of "C:/Users/David Traparic/Documents/prog/HITNet/HIT-master/hit/csrc/cuda/ROIAlign3d_cuda.cu".
error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin\\nvcc.exe' failed with exit code 1

I'm not very good in C compilation and low-level errors, do somebody knows what all this means ?

David

Thank you for your work!
During the inference or val, the actor bounding box is from the detection result of YOWO? If so, could you provide the corresponding val annotations?
Thank you very much！

Thank you very much for your excellent work. It appears that the links for the SlowFast and JHMDB models in MODEL_ZOO.md are broken. The SlowFast may be the same as the one published in HIT_ava's MODEL_ZOO.md. Could you please fix the links? Thank you.

Hello author, when I use your pretrained model to run inference and run training code , both of them have error occurred:
the following is train code part:

2024-03-13 14:00:53,800 hit.trainer INFO: Start training
Traceback (most recent call last):
File "train_net.py", line 255, in
main()
File "train_net.py", line 245, in main
args.no_head)
File "train_net.py", line 100, in train
mem_active,
File "/home/hscc/Desktop/chris/HIT/hit/engine/trainer.py", line 59, in do_train
loss_dict, weight_dict, metric_dict, pooled_feature = model(slow_video, fast_video, boxes, objects, keypoints, mem_extras)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/detector/action_detector.py", line 20, in forward
result, detector_losses, loss_weight, detector_metrics = self.roi_heads(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/roi_heads_3d.py", line 12, in forward
result, loss_action, loss_weight, accuracy_action = self.action(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/action_head.py", line 44, in forward
x, x_pooled, x_objects, x_keypoints, x_pose = self.feature_extractor(slow_features, fast_features, proposals, objects, keypoints, extras, part_forward)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/roi_action_feature_extractor.py", line 145, in forward
ia_feature, res_person, res_object, res_keypoint = self.hit_structure(person_pooled, proposals, object_pooled, objects, hands_pooled, keypoints, memory_person, None, None, phase="rgb")
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/hit_structure.py", line 213, in forward
mem_feature, phase)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/hit_structure.py", line 230, in _reduce_dim
query = self.person_dim_reduce(person)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 590, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 586, in _conv_forward
input, weight, bias, self.stride, self.padding, self.dilation, self.groups
TypeError: conv3d() received an invalid combination of arguments - got (Tensor, Parameter, Parameter, tuple, tuple, tuple, int), but expected one of:

• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)
• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)

and folliwing is inference code part：

2024-03-13 14:04:58,243 hit.inference INFO: Start evaluation on jhmdb_val dataset(9121 videos).
2024-03-13 14:04:58,249 hit.inference INFO: Stage 1: extracting clip features.
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1141/1141 [10:33<00:00, 1.80it/s]
2024-03-13 14:15:31,295 hit.inference INFO: Stage 1 time: 0:10:33.046037 (0.06940533238902268 s / video per device, on 1 devices)
2024-03-13 14:15:31,296 hit.inference INFO: Stage 2: predicting with extracted feature.
0%| | 0/1141 [00:00<?, ?it/s]
Traceback (most recent call last):
File "test_net.py", line 95, in
main()
File "test_net.py", line 89, in main
output_folder=output_folder,
File "/home/hscc/Desktop/chris/HIT/hit/engine/inference.py", line 182, in inference
predictions = compute_on_dataset(model, data_loader, device, logger, mem_active)
File "/home/hscc/Desktop/chris/HIT/hit/engine/inference.py", line 139, in compute_on_dataset
results_dict = compute_on_dataset_2stage(model, data_loader, device, logger)
File "/home/hscc/Desktop/chris/HIT/hit/engine/inference.py", line 116, in compute_on_dataset_2stage
output = model(None, None, None, None, extras=extras, part_forward=1)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/detector/action_detector.py", line 20, in forward
result, detector_losses, loss_weight, detector_metrics = self.roi_heads(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/roi_heads_3d.py", line 12, in forward
result, loss_action, loss_weight, accuracy_action = self.action(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/action_head.py", line 44, in forward
x, x_pooled, x_objects, x_keypoints, x_pose = self.feature_extractor(slow_features, fast_features, proposals, objects, keypoints, extras, part_forward)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/roi_action_feature_extractor.py", line 145, in forward
ia_feature, res_person, res_object, res_keypoint = self.hit_structure(person_pooled, proposals, object_pooled, objects, hands_pooled, keypoints, memory_person, None, None, phase="rgb")
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/hit_structure.py", line 213, in forward
mem_feature, phase)
File "/home/hscc/Desktop/chris/HIT/hit/modeling/roi_heads/action_head/hit_structure.py", line 230, in _reduce_dim
query = self.person_dim_reduce(person)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 590, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/home/hscc/anaconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 586, in _conv_forward
input, weight, bias, self.stride, self.padding, self.dilation, self.groups
TypeError: conv3d() received an invalid combination of arguments - got (Tensor, Parameter, Parameter, tuple, tuple, tuple, int), but expected one of:

• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)
• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)

hope you can tell me how to solve this problem
thanks.

How can I run the provided code if the model is missing, and what and which files modifications are necessary to initiate training for this model?

Hello author, I am very interested in your article, try to reproduce it. But the error, show can not find hit._custom_cuda_ext, where is this file

When I was training ava dataset, the following error occurred. How should I solve it?

Hello, author. May I know how to calculate frame mAP？Thank you very much.

I am trying to train the model (JHMDB) with the weights SlowFast-ResNet50-4x16.pth (soft link created) at path HIT/data/models/pretrained_models/

However, when I try to train the model using python train_net.py --config-file "config_files/hitnet.yaml" I get an error saying that Conv3D received invalid arguments:

conv3d() received an invalid combination of arguments - got (Tensor, Parameter, Parameter, tuple, tuple, tuple, int), but expected one of:
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (�[32;1mTensor�[0m, �[31;1mParameter�[0m, �[31;1mParameter�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[32;1mint�[0m)
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (�[32;1mTensor�[0m, �[31;1mParameter�[0m, �[31;1mParameter�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[32;1mint�[0m)
  File "/home/stdf/HIT/hit/modeling/roi_heads/action_head/hit_structure.py", line 230, in _reduce_dim
    query = self.person_dim_reduce(person)
  File "/home/stdf/HIT/hit/modeling/roi_heads/action_head/hit_structure.py", line 213, in forward
    mem_feature, phase)
  File "/home/stdf/HIT/hit/modeling/roi_heads/action_head/roi_action_feature_extractor.py", line 145, in forward
    ia_feature, res_person, res_object, res_keypoint = self.hit_structure(person_pooled, proposals, object_pooled, objects, hands_pooled, keypoints, memory_person, None, None, phase="rgb")
  File "/home/stdf/HIT/hit/modeling/roi_heads/action_head/action_head.py", line 44, in forward
    x, x_pooled, x_objects, x_keypoints, x_pose = self.feature_extractor(slow_features, fast_features, proposals, objects, keypoints, extras, part_forward)
  File "/home/stdf/HIT/hit/modeling/roi_heads/roi_heads_3d.py", line 12, in forward
    result, loss_action, loss_weight, accuracy_action = self.action(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
  File "/home/stdf/HIT/hit/modeling/detector/action_detector.py", line 20, in forward
    result, detector_losses, loss_weight, detector_metrics = self.roi_heads(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
  File "/home/stdf/HIT/hit/engine/trainer.py", line 59, in do_train
    loss_dict, weight_dict, metric_dict, pooled_feature = model(slow_video, fast_video, boxes, objects, keypoints, mem_extras)
  File "/home/stdf/HIT/train_net.py", line 100, in train
    mem_active,
  File "/home/stdf/HIT/train_net.py", line 245, in main
    args.no_head)
  File "/home/stdf/HIT/train_net.py", line 255, in <module>
    main()
TypeError: conv3d() received an invalid combination of arguments - got (Tensor, Parameter, Parameter, tuple, tuple, tuple, int), but expected one of:
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (�[32;1mTensor�[0m, �[31;1mParameter�[0m, �[31;1mParameter�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[32;1mint�[0m)
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (�[32;1mTensor�[0m, �[31;1mParameter�[0m, �[31;1mParameter�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[31;1mtuple�[0m, �[32;1mint�[0m)

This error is possibly originating at the reduce_person_dim function. Am I using the project incorrectly? Can you help me fix this?

Is there anything keypoint needs to modify for ava data set? Why does the following error occur?

Hello author, I am very interested in your work and see that your code uses a loss function of your own design, but the article does not mention what loss function you use in your work. Can you tell me what method you use for this loss function.Thank you very much!

Hello, can you provide a demo script to display the visualization results?

Hello author ,I have successfully compiled the hit library on the linux system but not the pip install-e. compile in window. Do you know what versions of vs and ninija to compile on the window system?Thanks so much for your reply.

Hello author, I found that the weights of some parameters were not loaded during the training process, will this affect the final training results and mAP calculation? If so, what is the cause? Is the weight file I loaded incomplete? Could the author give me some suggestions, thank you very much.
Here are some log messages from the training process:
2023-11-12 10:39:16,803 hit.utils.model_serialization INFO: backbone.slow.res_nl4.res_2.btnk.conv3.bn.weight loaded from backbone.slow.res_nl4.res_2.btnk.conv3.bn.weight of shape (2048,)
2023-11-12 10:39:16,803 hit.utils.model_serialization INFO: backbone.slow.res_nl4.res_2.btnk.conv3.conv.weight loaded from backbone.slow.res_nl4.res_2.btnk.conv3.conv.weight of shape (2048, 512, 1, 1, 1)
2023-11-12 10:39:16,803 hit.utils.model_serialization INFO: roi_heads.action.feature_extractor.fc1.bias will not be loaded.
2023-11-12 10:39:16,803 hit.utils.model_serialization INFO: roi_heads.action.feature_extractor.fc1.weight will not be loaded.

Hi,
I have read your paper. It's very interesting. I am working in the same research area. Can you please provide your pretrained model on Multi Sports Dataset? It would really help my research.

Thanks,
Rohit Girmaji

I tried running python train_net.py --config-file "config_files/hitnet.yaml", but I encountered the following error. Could you advise on how to resolve this? I installed PyTorch 1.10.0. Thank you.

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [8, 1024]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

Can you provide a demo script to display the visualization results?

HIT-master$ python test_net.py --config-file "config_files/hitnet.yaml" MODEL.WEIGHT "data/models/J-HMDB/model_J-HMDB.pth"
Traceback (most recent call last):
File "test_net.py", line 8, in
from hit.modeling.detector import build_detection_model
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/modeling/detector/init.py", line 1, in
from .action_detector import build_detection_model
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/modeling/detector/action_detector.py", line 3, in
from ..backbone import build_backbone
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/modeling/backbone/init.py", line 1, in
from .backbone import build_backbone
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/modeling/backbone/backbone.py", line 2, in
from . import slowfast, i3d
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/modeling/backbone/slowfast.py", line 6, in
from hit.modeling.common_blocks import ResNLBlock
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/modeling/common_blocks.py", line 2, in
from hit.modeling.nonlocal_block import NLBlock
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/modeling/nonlocal_block.py", line 6, in
from hit.layers import FrozenBatchNorm3d
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/layers/init.py", line 3, in
from .roi_align_3d import ROIAlign3d
File "/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/HIT-master/hit/layers/roi_align_3d.py", line 7, in
import hit._custom_cuda_ext as _C
ImportError: libtorch_cuda_cu.so: cannot open shared object file: No such file or directory

i already install hit
Using /home/user/anaconda3/envs/hit/lib/python3.8/site-packages
Finished processing dependencies for hit==0.0.0

Link redirection to master branch!
Any other link to get the pretrained ?

Hello, can you tell me what the map value in the AVA dataset is when SlowFast-Resnet50 is used as the backone?

Thank you for the author's reply, but why is the value of video mAP that I received significantly different from the value given in your paper, about 3% or 5%? Should I make modifications to certain parameters to achieve the results shown in your paper？I hope the author can provide some suggestions. Thank you very much

when i meet this error ,i think there is something wrong with the path , but i just can not find the module '_custom_cuda_ext' in my project ,could you tell me how to fix this error?

Hello author, I am now trying to use two Gpus for distributed training, but I do not know why I have been staying here and did not start training, may I ask you to encounter such a situation?

The following error occurs when executing "python train_net.py --config-file "config_files/hitnet.yaml"

Traceback (most recent call last):
File "train_net.py", line 255, in
main()
File "train_net.py", line 245, in main
args.no_head)
File "train_net.py", line 100, in train
mem_active,
File "/root/autodl-tmp/HIT-master/hit/engine/trainer.py", line 59, in do_train
loss_dict, weight_dict, metric_dict, pooled_feature = model(slow_video, fast_video, boxes, objects, keypoints, mem_extras)
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/HIT-master/hit/modeling/detector/action_detector.py", line 20, in forward
result, detector_losses, loss_weight, detector_metrics = self.roi_heads(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/HIT-master/hit/modeling/roi_heads/roi_heads_3d.py", line 12, in forward
result, loss_action, loss_weight, accuracy_action = self.action(slow_features, fast_features, boxes, objects, keypoints, extras, part_forward)
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/HIT-master/hit/modeling/roi_heads/action_head/action_head.py", line 44, in forward
x, x_pooled, x_objects, x_keypoints, x_pose = self.feature_extractor(slow_features, fast_features, proposals, objects, keypoints, extras, part_forward)
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/HIT-master/hit/modeling/roi_heads/action_head/roi_action_feature_extractor.py", line 145, in forward
ia_feature, res_person, res_object, res_keypoint = self.hit_structure(person_pooled, proposals, object_pooled, objects, hands_pooled, keypoints, memory_person, None, None, phase="rgb")
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/HIT-master/hit/modeling/roi_heads/action_head/hit_structure.py", line 213, in forward
mem_feature, phase)
File "/root/autodl-tmp/HIT-master/hit/modeling/roi_heads/action_head/hit_structure.py", line 230, in _reduce_dim
query = self.person_dim_reduce(person)
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 590, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/root/miniconda3/envs/hit/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 586, in _conv_forward
input, weight, bias, self.stride, self.padding, self.dilation, self.groups
TypeError: conv3d() received an invalid combination of arguments - got (Tensor, Parameter, Parameter, tuple, tuple, tuple, int), but expected one of:

• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)
• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)

I hope the author can give some answers. Thank you very much

ImportError:hit/_custom_cuda_ext.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda20getCurrentCUDAStreamEa
my torch is 1.7.1+cu101

Thanks a lot ! Could you please tell us how to prepare other datasets ( UCF101、AVA) step by step ?

We have modified and run the code of AVA dataset, and the error appears as follows. May I ask how to solve it？

Is the code for calculating video map public?
I haven't seen it in this hub. If not, can you share it?