umairjavaid

How can I implement this post processing step in FastMOT ``` def yolox_nano_postprocess(self, prediction, num_classes=2, conf_thre=0.01, nms_thre=0.65, class_agnostic=True): print("#" * 100) box_corner = prediction.copy() print("box corner shape : {}".format(box_corner.shape)) box_corner[:,...

I am trying to Implement YOLOX in FastMOT. Can you tell me if I need to modify preprocessing for the Yolo class. Here's the preprocessing code of YoloX. Can I...

Open source contribution

1

I came across this repo while I was working looking for a profiling tool. I want to study profilers in depth. I'm willing to make any opensource contribution to this...

where are benchmark results being saved?

1

I have downloaded the latest docker image. I can't find the model benchmark results. model = resnet50-v2 command for benchmark `python tools/converter.py run --config=mace-models/resnet-v2-50/resnet-v2-50.yml --benchmark --debug_mode --report` ```` CMD> bazel...

ERROR: [RUN] /home/umair/Desktop/umair/mace/tools/device.py:290: Failed to run the model

1

Getting the following error when trying to run mobilenet-v2 on GPU. **commands:** ``` python tools/converter.py convert --config=mace-models/mobilenet-v2/mobilenet-v2-host.yml python tools/converter.py run --config=mace-models/mobilenet-v2/mobilenet-v2-host.yml ``` **mobilenet-v2-host.yml:** ``` library_name: mobilenet-v2-host target_abis: [host] model_graph_format: file...

getting the following error when building nimble in conda enviornment FAILED: caffe2/CMakeFiles/torch_cuda.dir/utils/torch_cuda_generated_math_gpu.cu.o subprocess.CalledProcessError: Command '['cmake', '--build', '.', '--target', 'install', '--config', 'Release', '--', '-j', '8']' returned non-zero exit status 1.

4

``` [46/402] Building NVCC (Device) object...ils/torch_cuda_generated_math_gpu.cu.o FAILED: caffe2/CMakeFiles/torch_cuda.dir/utils/torch_cuda_generated_math_gpu.cu.o cd /home/umair/Desktop/umair/nimble2/nimble/build/caffe2/CMakeFiles/torch_cuda.dir/utils && /home/umair/anaconda3/envs/nimble/bin/cmake -E make_directory /home/umair/Desktop/umair/nimble2/nimble/build/caffe2/CMakeFiles/torch_cuda.dir/utils/. && /home/umair/anaconda3/envs/nimble/bin/cmake -D verbose:BOOL=OFF -D build_configuration:STRING=Release -D generated_file:STRING=/home/umair/Desktop/umair/nimble2/nimble/build/caffe2/CMakeFiles/torch_cuda.dir/utils/./torch_cuda_generated_math_gpu.cu.o -D generated_cubin_file:STRING=/home/umair/Desktop/umair/nimble2/nimble/build/caffe2/CMakeFiles/torch_cuda.dir/utils/./torch_cuda_generated_math_gpu.cu.o.cubin.txt -P /home/umair/Desktop/umair/nimble2/nimble/build/caffe2/CMakeFiles/torch_cuda.dir/utils/torch_cuda_generated_math_gpu.cu.o.Release.cmake /home/umair/Desktop/umair/nimble2/nimble/caffe2/utils/math_gpu.cu(149): warning: the...

In your scorecam implementation, why are you normalizing all the activations together? Why not normalize each activation map independently in a loop? Are these two the same?