Devymex
[help]How to export swin model to ONNX? Problem: Node (Concat_246) Op (Concat) [ShapeInferenceError]
For exporting the video swin transformer to onnx (opcode=9), following code works and compatible with TensorRT 7. https://gist.github.com/devymex/51687edd41eef4ccc56d76a0c66bf92c P.s. The default config is for Swin-T and its pretrained model can...
## 1. Convert llama-2 from HuggingFace to Megatron-LM: ``` PYTHONPATH=$(pwd) tools/checkpoint/util.py --model-type=GPT --loader=llama2_hf --load-dir= --save-dir= --tokenizer-model= ``` ## 2. Convert llama-2 from Megatron-LM to HuggingFace: Step 1. Download this [python...
> There are several options for cvtColor for this: > > -- | -- COLOR_RGB2YUV_I420 Python: cv.COLOR_RGB2YUV_I420 | RGB to YUV 4:2:0 family. COLOR_BGR2YUV_I420 Python: cv.COLOR_BGR2YUV_I420 | COLOR_RGB2YUV_IYUV Python: cv.COLOR_RGB2YUV_IYUV...
Found the same problem