fizyr / keras-retinanet

Keras implementation of RetinaNet object detection.
Apache License 2.0
4.38k stars 1.96k forks source link

TypeError: type object got multiple values for keyword argument 'training' #1412

Closed patagona-snayyer closed 4 years ago

patagona-snayyer commented 4 years ago

When I run the command: retinanet-train csv path/to/annotations.csv path/to/classes.csv

I get this error :

C:\Users\Saahil Nayyer\AppData\Roaming\Python\Python37\site-packages\keras_resnet\layers_batch_normalization.py:17 call return super(BatchNormalization, self).call(training=(not self.freeze), args, **kwargs)

TypeError: type object got multiple values for keyword argument 'training'

I looked up the reason for the error and it turns out the first argument in call() should be self perhaps, but that again doesn't really help.

After many failed attempts with Faster-RCNN I have switched to Keras, please help me I'm stuck. Thank you in advance!

dalalams commented 4 years ago

I fixed it by updating Keras pip install --upgrade keras==2.3.0

patagona-snayyer commented 4 years ago

I fixed it by updating Keras pip install --upgrade keras==2.3.0

Thank you @damasubaie . It worked.