zhaogangthu

> onnx dynamic model 转trt model 推理结果不正确，请问是可能由于什么原因呢 我当时遇到的主要问题是数据没有对齐： _trt_outputs = common.do_inference_v3(self.context, bindings=self.bindings, inputs=self.inputs, outputs=self.outputs, stream=self.stream, h_=h_, w_=w_ ) scale_w=w_/608 scale_h=h_/608 output_shapes = [(1, int(h_/32), int(w_/32), 21), (1, int(h_/16), int(w_/16), 21),...

> Hi, > > I went through your code and description. I want to train this network on my own dataset. How to achieve that?? > I want to train...

hi, If number plates have fixed size and position for Letters, I think this task is more easier，because you don't need train a yolo model which is to detect text...

> Thanks for your detailed explanation. > > Can you provide your dataset used for training and testing it?? I can replicate the same thing my dataset. Sorry, we have...

> Okay. No problem. > > But could you provide 2-3 sample data with label to run evaluation script with your model. > It would be nice to get some...

> Thank you. Got it. The dataset should be Images : Image001.jpg, image002.jpg .... Labels : is it a txt file?? If my image has ABZ-2090 in it. Then my...