Yet-Another-EfficientDet-Pytorch-Convert-ONNX-TVM

Yet-Another-EfficientDet-Pytorch-Convert-ONNX-TVM copied to clipboard

不好意思，想要請教您 我在轉換為TVM時，出現了以下的warning，TVM的版本為0.9 所以在您下面需要修改的部分已經有些不一樣了 /home/youwh/ywh/efficientDet--ONNX/efficientnet/utils_extra.py:37: TracerWarning: Converting a tensor to a NumPy array might cause the trace to be incorrect. We can't record the data flow of Python values, so this...

andrewwang0612

TensorRT

1

模型转成ONNX后再TensorRT中调用出现： `ERROR: Parameter check failed at: ../builder/Network.cpp::addPoolingNd::690, condition: allDimsGtEq(windowSize, 1) && volume(windowSize) < MAX_KERNEL_DIMS_PRODUCT` 的错误。请问在TensorRT下你们是否测试过。非常感谢！！！

DataXujing

I use your code convert to onnx，but the onnx can not use to tensorrt

2

qiuzhizhe

python convert/convert_onnx.py Traceback (most recent call last): File "/home/jliu/data2/Yet-Another-EfficientDet-Pytorch-Convert-ONNX-TVM/convert/convert_onnx.py", line 4, in from backbone import EfficientDetBackbone ImportError: cannot import name 'EfficientDetBackbone' from 'backbone' (/home/jliu/anaconda3/envs/adabins/lib/python3.9/site-packages/backbone/__init__.py)

azuryl

RuntimeError: ONNX export failed: Couldn't export Python operator SwishImplementation

7

I ran your convert to onnx code and had error like title, can you help?

nutsam

I can convert efficientdet-d0.pth to onnx! I want convert other pre-trained models such as efficientdet-d1.pth. how to rewrite convert/convert_onnx.py for convert efficientdet-d1.pth?

kmaeda1224

Hey there, I'm having trouble using the converted model in onnxjs. I used the pretrained D0 model and the demo convert command: ``` python3 convert/convert_onnx.py ``` After successfull export, this...

radiachkik

onnxruntime推理出错

3

Hello, this error occurred when I was reasoning on onnxruntime. Have you ever encountered it？Thank you very much if you can reply！ onnxruntime.capi.onnxruntime_pybind11_state.InvalidGraph: [ONNXRuntimeError] : 10 : INVALID_GRAPH : Load...

youwh-PIRI

Hi @murdockhou I ran with both original model of author and the converted version to Onnx. But I found that the output anchors of original model was torch.Size([1, 196416, 4]),...

hieubz

can you provide a demo,just like use c++ and your onnx model to predict ，maybe it is like efficientdet_video.py. thank you！

zuop-star