loiccordone / object-detection-with-spiking-neural-networks

Repository code for the IJCNN 2022 paper "Object Detection with Spiking Neural Networks on Automotive Event Data"
MIT License
57 stars 12 forks source link

Replication of Classification Results: 'Namespace' object has no attribute 'undersample_cars_percent' #10

Closed ghost closed 2 years ago

ghost commented 2 years ago

Hello Loic, I am stuck while replicating your classification results. Could you please help me if you know how to fix this error? I can run object detection code flawlessly now however I am stuck while trying to replicate your classification results.

(myenv) sh-4.2$ python classification.py -dataset gen1 -path datasets/gen1 -model densenet121-16 -T 5 -tbin 2
Namespace(T=5, b=64, bn=True, dataset='gen1', device=0, epochs=30, image_shape=(304, 240), lr=0.005, model='densenet121-16', path='datasets/gen1', precision=16, pretrained=None, sample_size=100000, save_ckpt=False, tbin=2, test=False, train=True)
File loaded.
Traceback (most recent call last):
  File "classification.py", line 90, in <module>
    main()
  File "classification.py", line 50, in main
    train_dataset = dataset(args, mode="train")
  File "/home/ec2-user/SageMaker/datasets/classification_datasets.py", line 108, in __init__
    self.undersample_cars_percent = args.undersample_cars_percent
AttributeError: 'Namespace' object has no attribute 'undersample_cars_percent'

Below are screenshots. err error Regards,