👨‍💻Every day problems solution given in 30DaysOfCode contest held on Hackerrank. Note: Solution of every problem is given after the contest is over. So first try to solve by yourself then see the solution. All the best 👍 GitHub View Github    

Background Challenge link: https://lpcv.ai/2021LPCVC/fpga-track Leaderboard: https://lpcv.ai/scoreboard/FPGA21 Environment Xilinx Board: Ultra-96 V2 System: https://github.com/Avnet/Ultra96-PYNQ/releases v2.6 git clone –recursive –shallow-submodules https://github.com/Xilinx/DPU-PYNQ cd DPU-PYNQ/upgrade make pip3 install pynq-dpu Note: replace the image.ub with the LPCV provided one. Build cd nms python3 build.py install Evaluation Evaluate in the jupyternote book: evaluation.ipynb. Contributors Jiahao Hu, Pu Li, Yongqiang Yao, Ruihao Gong Reference Links The detection model    

The 2nd place solution of 2021 google landmark retrieval on kaggle. Environment We use cuda 11.1/python 3.7/torch 1.9.1/torchvision 0.8.1 for training and testing. Download imagenet pretrained model ResNeXt101ibn and SEResNet101ibn from IBN-Net. ResNest101 and ResNeSt269 can be found in ResNest. Prepare data Download GLDv2 full version from the official site. Run python tools/generate_gld_list.py. This will generate clean, c2x, trainfull and all data for different stage of training. Validation annotation comes from all 1129 images in GLDv2. We expand the competition […]