tkDNN
tkDNN copied to clipboard
ceccocats
Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms
I have generated a `.rt` (`.plan`) file of a trained `yolo4tiny` Darknet model by passing the `weights`, `input_bins` and `out_bins` to `tests/darknet/yolo4tiny.cpp`. When I try to serve the generated `.plan`...
i changed conf_treshhold from 0.3 to 0.001 and tried calibration with 4951 images and still mAP is very bad compared to int8 of yolo4 , the mAP just increased for...
HI I would like to run the demo with my own custom yolov4 model. Is it that I have to make sure that there is a test_nn folder in the...
Can't upgrade to cmake3.5 in arm64 and ubuntu 18. This is what happens with the project with cmake 3.2. For using it, I've used commit 62e4a3f779053123f9f18370eb63f8b3595bc92a for this repositoy, the...
I don't understand something that looks like simple, but is weird at the same time. I need to compile in arm64 which newest version is 3.2 . You jumped at...
There's couple issues with exporting weights from darknet: - the darknet fork is broken, there are unmerged changes in [convolution_kernels.cu](https://git.hipert.unimore.it/fgatti/darknet/-/blob/master/src/convolutional_kernels.cu#L851) - fopen mode in [darknet.c](https://git.hipert.unimore.it/fgatti/darknet/-/blob/master/src/darknet.c#L455) is wrong (should be "wb")...
 I changed my CMaKeLists,txt into the master branch version and I replace the "unistd.h" with "windows.h" and now I met this new problem,I think the reson for that maybe...
### Is it possible to build on Windows? - **Setting** OS : Windows10 GPU : Titan XP(CUDA10.1, CuDNN_v7.6.5) CPU : AMD OpenCV : 4.3.0 #### 1. When i compiled it...
I noticed that sometimes the output bbox cross the image border. I run yolov4 coco model "yolo4_fp16_416_b4.rt". My video frame is 1920x1080, the output has the format and get the...
