Visualize the three channels of YOLOv5 backbone in 15min to get started det ,process blocked

[ding19980201]

Prerequisite

• I have searched the existing and past issues but cannot get the expected help.
• I have read the FAQ documentation but cannot get the expected help.
• The bug has not been fixed in the latest version.

🐞 Describe the bug

python demo/featmap_vis_demo.py data/cat/images/IMG_20221020_112705.jpg \
                                configs/yolov5/yolov5_s-v61_fast_1xb12-40e_cat.py \
                                work_dirs/yolov5_s-v61_fast_1xb12-40e_cat/epoch_40.pth \
                                --target-layers backbone \
                                --channel-reduction squeeze_mean

HERE IS display

(DYX-MMLAB) dyx@dyx-MS-7C82:~/project/mmyolo$ python demo/featmap_vis_demo.py data/cat/images/IMG_20221020_112705.jpg \
>                                 configs/yolov5/yolov5_s-v61_fast_1xb12-40e_cat.py \
>                                 work_dirs/yolov5_s-v61_fast_1xb12-40e_cat/epoch_40.pth \
>                                 --target-layers backbone \
>                                 --channel-reduction squeeze_mean
!!!You are using `YOLOv5Head` with num_classes == 1. The loss_cls will be 0. This is a normal phenomenon.
Loads checkpoint by local backend from path: work_dirs/yolov5_s-v61_fast_1xb12-40e_cat/epoch_40.pth
04/09 11:29:52 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io
04/09 11:29:52 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future.
04/09 11:29:54 - mmengine - WARNING - `Visualizer` backend is not initialized because save_dir is None.
[                                                  ] 0/1, elapsed: 0s, 
ETA:/home/dyx/anaconda3/envs/DYX-MMLAB/lib/python3.9/site-packages/mmengine/visualization/visualizer.py:968: UserWarning: Since the spatial dimensions of overlaid_image: (3000, 4000) and featmap: torch.Size([80, 80]) are not same, the feature map will be interpolated. This may cause mismatch problems ！
  warnings.warn(
^Z
[1]+  已停止               python demo/featmap_vis_demo.py data/cat/images/IMG_20221020_112705.jpg configs/yolov5/yolov5_s-v61_fast_1xb12-40e_cat.py work_dirs/yolov5_s-v61_fast_1xb12-40e_cat/epoch_40.pth --target-layers backbone --channel-reduction squeeze_mean

i can do nothing as the computer be blocked
i can only restart my conputer

Environment

sys.platform: linux
Python: 3.9.16 (main, Mar 8 2023, 14:00:05) [GCC 11.2.0]
CUDA available: True
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 3070
CUDA_HOME: /usr
NVCC: Cuda compilation tools, release 9.1, V9.1.8
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.12.1+cu113
PyTorch compiling details: PyTorch built with:

• GCC 9.3
• C++ Version: 201402
• Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• LAPACK is enabled (usually provided by MKL)
• NNPACK is enabled
• CPU capability usage: AVX2
• CUDA Runtime 11.3
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
• CuDNN 8.3.2 (built against CUDA 11.5)
• Magma 2.5.2
• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

TorchVision: 0.13.1+cu113
OpenCV: 4.7.0
MMEngine: 0.7.0
MMCV: 2.0.0rc4
MMDetection: 3.0.0rc6
MMYOLO: 0.5.0+dc85144

进程已结束,退出代码0

Additional information

AS I CREATE environment including mmdetection mmtracking mmyolo they are all using openmmlab2.0
i DONT follow the environment create turtoils strictly
perhaps it is the reason
HOWEVER I CAN train well on this environment @lindahua @grimoire @zhiqwang @lvhan028 @

[ding19980201]

some problems happen to my env. I test on another computer ,i runs well

[ding19980201]

I have debuged again it is very slow but it runs successfully. my image shape is 3000,4000,3 I guess it is very hard to run this big shape . However i run command following the turtail. does anyone have the same problem??

[ding19980201]

thefirst featmap is 12830004000 and it equals about 6GB the second and third is 25630004000 51230004000 @grimoire @lindahua @zhiqwang @lvhan028

[hhaAndroid]

@ding19980201 If the input size is too large, it can indeed cause many problems. For now, we haven't considered such large inputs.