3d poser online8/2/2023 ![]() This API takes care of any preprocessing the image needs (resizing, etc) cf_openpose_aichallenger_368_368_0.3_189.7G which can be found in Vitis AI Model Zooĭoing inference with OpenPose is quite simple: auto image = cv::imread("sample_openpose.jpg") auto det = vitis::ai::OpenPose::create("openpose_pruned_0_3") auto results = det->run(image).The TensorFlow2 and Vitis AI design flow is described in this tutorial. Python train-res.py python -u quantize.py -float_model model/residual/res.h5 -quant_model model/residual/quant_res.h5 -batchsize 64 -evaluate 2>&1 | tee quantize.log vai_c_tensorflow2 -model model/residual/quant_res.h5 -arch /opt/vitis_ai/compiler/arch/DPUCVDX8H/VCK5000/arch.json -output_dir model/residual -net_name res a DNN with fewer neurons on each layer but with more layers than the one described in the article (res.xmodel):.The docker_run.sh file was modified to add support for X11 and USB webcams: docker_run_params=$(cat &1 | tee quantize.log vai_c_tensorflow2 -model model/article/quant_article.h5 -arch /opt/vitis_ai/compiler/arch/DPUCVDX8H/VCK5000/arch.json -output_dir model/article -net_name article Clone the Yoga AI repository in the Vitis AI directory.Run the openpose demo to verify everything is installed correctly.If you have a VCK5000-PROD card then the latest Vitis AI library will have a similar page describing how to do it Setup VCK5000-ES1 Card as described here.(Tip: the GPU Docker build requires a lot of DRAM, if your build fails consider enabling swap ) For training and model quantization the GPU Docker needs to be build as it will speed up the process considerably. GANs are notoriously hard to train, the state where both the discriminator and the generator are producing good results being a fleeting state rather than a stable one. The model was trained on images obtained from 35 videos found on YouTube about yoga poses. ![]() Both the generator and the discriminator are trained together, one's goal being to create "fake" 2D poses while the other's is to detect the "fakes". The main idea is that if the generator will be able to create good estimation of 3D poses then those 3D poses randomly rotated and projected back in 2D will look indistinguishable for the discriminator. They are then fed back to the discriminator. The 3D poses generated by the generator are randomly rotated, transformed back to the camera's coordinates and projected back in 2D. The discriminator's job is to take 2D poses and return if they are real or fake (generated by the generator). The generator's job is to take 2D poses and generate the depth for them, transforming them in 3D poses. This model consists in a generator (the residual model was used) and a discriminator. The third model, referred as gan (gan.xmodel) uses a novel idea: a generative adversarial network to generate 3D data only from 2D data. As far as the author is aware this is the only dataset available with 3D data. ![]() This contains 3D data obtained from using expensive high resolution cameras setup in a studio, filming professional actors. The two models are trained on the Human3.6M dataset. This alternative model is referred further as "residual" or "res.xmodel". The model proposed in this article will be referred further on as the "article model" or the article.xmodel (from the file name used to do inference on the VCK5000 card).Īn alternative to the "article" model was tried, with fewer neurons on a layer but with more layers. The first article explores a simple yet effective way to "lift" the 2D data to 3D by using a relatively simple DNN.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |