yolact_edge: About custom dataset with TensorRT RuntimeError

Sorry to bother you… I retrained my custom dataset to detect only person class.

But when I used the model to evaluate,it showed the error about “Expected 3 elements in a list but found 2”…

Did anyone meet the error before ?

I also used --use_fp16_tensorrt command ,and it still get the error.

I think maybe it’s overfitting,so it can’t transfer tensorrt properly.

Did it possible ?

Here’s my config.py

person_dataset=dataset_base.copy({
    'name': 'person',
    
    'train_info': '/home/jason/dataset/mscoco/train2017_person.json',
    'valid_info': '/home/jason/dataset/mscoco/val2017_person.json',
    'class_names':("person",),
    'label_map': {1:1},
})

Thanks for your reading~