kaierlong
kaierlong
gcc/g++: 9.3.0 cmake: 3.20.2 protobuf: 3.13.0 hdf5: 1.12.0 lightseq: master nvidia driver: 470.82.01 cuda: 11.4, V11.4.152 GPU: Tesla T4 OS: Ubuntu 20.04 x86_64 Docker image: nvcr.io/nvidia/tritonserver:21.07-py3 I build the `libtransformer_server.so`...
version log: 1. supported python3.x 2. modify some codes to support tensorflow 1.8.0 test info: test machine platform: Ubuntu 16.04.5 x86_64 GPU test python version: 3.5.2 test tensorflow version: 1.8.0...
> In your config file (experiments/coco/omnipose_w48_384x288.yaml), there is a parameter "PRETRAINED: 'weights/coco/OmniPose_w48_v2/model_best.pth'". > I wonder where to get the model_best.pth. Is it from previous trained like omnipose_w48_256x192.yaml or other public...