search

ardianumam / Tensorflow-TensorRT

This repository is for my YT video series about optimizing a Tensorflow deep learning model using TensorRT. We demonstrate optimizing LeNet-like model and YOLOv3 model, and get 3.7x and 1.5x faster for the former and the latter, respectively, compared to the original models.
303 stars 110 forks source link

Why output_tensors=["Placeholder:0", "concat_9:0", "mul_9:0"] #16

Open float123 opened 5 years ago

float123 commented 5 years ago

I wan to know why output_tensors=["Placeholder:0", "concat_9:0", "mul_9:0"], these three nodes are not at the end of the model. And what does ":0" mean? Please advise，thank you. image

ardianumam commented 5 years ago

Why not at the end of model

Because after the network output, we still have further operation, such as loss calculation, etc.

what :0 is

It is tensorflow convention when we wanna call a value from a tensor by tensor name, we need to add :0 in the end of it.

float123 commented 5 years ago

Thank you very much for your reply，I am currently researching yolov3 to TensorRT，your project has helped me a lot. There is still a question I would like to ask，why do we choose output_tensor to be "concat_9" and "mul_9", or what are their return values? the model is very troubled by me.

ardianumam commented 5 years ago

Those only tensor names. Everyone can name the tensor any name he wants. Those output in object detector correspond to the outputs of classification and bonding box predictions.

Pidem commented 5 years ago

Hey, I am confused. Where did you get this model architecture from? Did you fork YunYang's model. More specifically, why is NMS part of your model ?

DongXinru commented 5 years ago

I wonder how you got your yolov3 model file