single object tracking inference is not giving correct result

[Balakumaran-kandula]

single object tracking output for video is not good , tried with siameseprn and stark models

[JingweiZhang12]

Please use this issue template to report your problems.

[Balakumaran-kandula]

---

name: Error report about: Inference results were very bad.

Thanks for your error report and we appreciate it a lot.

Checklist

1. I have searched related issues but cannot get the expected help.

Describe the bug The single object tracker pretrained models were loaded "https://download.openmmlab.com/mmtracking/pretrained_weights/sot_resnet50.model" and did inference using demo_sot.py file , the tracker moves out of the subject (tried for different classes ( human , car )) and also tried with different pretrained models (lasot, otb100, trackingnet , uav123 ..) , and i havent changed anything from the github code just tried to do inference. But the bounding box output from the video was not tracking the object i gave in the first frame. Do i have to tweek any hyperparameters in the config file or the code for inference ?

Reproduction

1. What command or script did you run? python3 demo/demo_sot.py configs/sot/siamese_rpn/siamese_rpn_r50_20e_lasot.py --input demo/demo.mp4 --output demo/test.mp4

2. Did you make any modifications on the code or config? Did you understand what you have modified? I have changed the device="cpu" in the inference file before the line model.to(device) in init_model function , Because it was not running while i tried to use gpu , it shows the warning as i mentioned below and then nothing happens..

3. What dataset did you use and what task did you run? I tried to do inference for videos with mostly objects as cars and human.

Environment

1. Please run python mmtrack/utils/collect_env.py to collect necessary environment information and paste it here. /opt/conda/lib/python3.7/site-packages/torch/cuda/init.py:125: UserWarning: NVIDIA GeForce RTX 3060 with CUDA capability sm_86 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_61 sm_70 sm_75 compute_37. If you want to use the NVIDIA GeForce RTX 3060 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name)) sys.platform: linux Python: 3.7.7 (default, May 7 2020, 21:25:33) [GCC 7.3.0] CUDA available: True GPU 0: NVIDIA GeForce RTX 3060 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 10.1, V10.1.24 GCC: gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 PyTorch: 1.6.0 PyTorch compiling details: PyTorch built with:

• GCC 7.3
• C++ Version: 201402
• Intel(R) Math Kernel Library Version 2020.0.1 Product Build 20200208 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• NNPACK is enabled
• CPU capability usage: AVX2
• CUDA Runtime 10.1
• 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_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
• CuDNN 7.6.3
• Magma 2.5.2
• Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -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 -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,

TorchVision: 0.7.0 OpenCV: 4.5.5 MMCV: 1.5.0 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.1 MMTracking: 0.13.0+88f92dd

3. You may add addition that may be helpful for locating the problem, such as
   • How you installed PyTorch [e.g., pip, conda, source]
   • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback none

[Balakumaran-kandula]

The video used for testing :

https://motchallenge.net/sequenceVideos/MOT16-08-raw.webm

[JingweiZhang12]

You didn't load the checkpoint we provide. Please refer to the tutorial for running the demo.