
                    For onnx, we pick up the best solutions provided by github life savers.
                    If google brings you here, you are so lucky! These life savers are angels, they have well solved your problems.
                    So do not waste time scrolling the original issue threads just to dig out solutions... 
                    Here you are, you are welcome. Then, go back to work!
                    

@OneDirection9
Here is what I ended up with Let me what you think. Note: create this issue for anybody who might come across the similar issue in the future 

tensorflow onnx import frozen graph with error "Input 0 of node X was passed float from Y:0 incompatible with expected float_ref."

Hi all I found a way to get it to work (not sure if it's a hack or not) Add #define TENSORRTAPI at the top of NvOnnxParser.h 

onnx tensorrt Error on python3 setup.py build

For now I temporarily modify the onnx graph inputs:


This seems to work with the tensorflow backend but I haven't tested it on any others 

onnx Dynamic dummy input when exporting a PyTorch model?

I met the same issue with pytorch 1.8 and the following code works for me: 🐛 Bug
I got the below error message when I try to test out the latest commit cff9263 on a new docker image

yolov5 RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation when running on Docker

I'm having the same issue as @cocoyen1995 using keras2onnx to convert a tf.keras model to ONNX 

onnx tensorrt dynamic shape

For those visiting this thread much later and are using newer versions of onnxruntime-gpu 

onnxruntime Onnxruntime Error in libcublas.so.10

I also had this issue with a model coming from PyTorch Here's an explanation of what I did to work around the problem:
This PyTorch model 

onnx tensorrt Gather in Upsample problem

have you tried to add


to the file where the bug occurs? My environment and problem:

Python3.7
PyTorch1.5
same as the requirements.txt

There is no problem for object detection

yolov5 No module named 'models'

@Mashood3624 good news 😃! Feature map visualization was added ✅ in PR #3804 by @Zigars today 

yolov5 How to visualize feature mapping on YOLOV5s?

@yongjingli you can go to see  #343 ❔Question
Hi buddy ,can you help me to explain the outputs of the onnx model ? I don't know how to convert the outputs to boxes ,labels and scores 

yolov5 how to convert the outputs of the yolov5.onnx to boxes ,labels and scores .

@hdnh2006 multi-stream capability is already built in Hi! I would like to apply yolov5 to multiple cameras 

yolov5 Question: is there a way to apply yolov5 to multiple streaming sources?

Here is the updated detect.py files which saves the bounding box as a separate image in 'test_images/results/'
actual results with input image and bounding box will be saved in 'yolov5\runs\detect\exp'
only bounding boxes cropped as image will be saved in 'yolo5/test_images/results' (manually create directory 1st)

yolov5 Crop and save bounding box. I found yolov4 can do and any for yolov5?

Thank you for commenting on this for a hobbyist like me who does DeepLearning as a hobby I am not an engineer or a researcher 

PINTO_model_zoo Is there an easy way to convert ONNX or PB from (NCHW) to (NHWC)?

To be complete don't forget to add the modifications of the class numbers (classes from 80 to 1) I know it's very obvious 

yolov3 SINGLE-CLASS TRAINING EXAMPLE

@yonglizhong  actually my project for bachelor thesis is still ongoing Hence I haven't created a proper github repository for documentation purposes However 

yolov3 Intel RealSense: LoadWebcam() instead of LoadStreams()

Hey everyone it appears that optimize_for_mobile from torch is what causes the incompatibility issue with coremltools 

yolov5 CoreML Export Error: export failure: 'torch._C.Node' object has no attribute 'ival'

@adityap27
To be clear here is what I get:
CPU inference time = 30ms NMS time added additional 15ms
CPU with openvino inference time = 17ms NMS not attempted 