[ABCNet trains its own model (1)]
[ABCNet trains its own model (2)]
predict
The previous section talked about how to modify the parameters to train our own data and get our own model. This section talks about how to modify the parameters to decode the results of the last layer
Modify the number of decoded labels and categories
Set the confidence threshold during inference
This function is in demo.py. If
you have any other questions, please leave a message.