关于在第一轮回调时的报错信息

[ghost]

在训练了1个epoch后，开始回调时出现了下面这个报错信息：

Traceback (most recent call last):
File "run.py", line 166, in
tf.app.run()
File "e:\Anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "run.py", line 157, in main
train_model(FLAGS)
File "D:\garbage_classification\garbage_classify-master\train.py", line 134, in train_model
shuffle=False
File "e:\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "e:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1732, in fit_generator
initial_epoch=initial_epoch)
File "e:\Anaconda3\lib\site-packages\keras\engine\training_generator.py", line 242, in fit_generator
workers=0)
File "e:\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "e:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1791, in evaluate_generator
verbose=verbose)
File "e:\Anaconda3\lib\site-packages\keras\engine\training_generator.py", line 341, in evaluate_generator
callbacks._call_begin_hook('test')
File "e:\Anaconda3\lib\site-packages\keras\callbacks\callbacks.py", line 105, in _call_begin_hook
self.on_test_begin()
File "e:\Anaconda3\lib\site-packages\keras\callbacks\callbacks.py", line 239, in on_test_begin
callback.on_test_begin(logs)
AttributeError: 'WarmUpCosineDecayScheduler' object has no attribute 'on_test_begin'

我的运行环境和作者的是一样的，用笔记本跑的代码，所以把调用GPU的代码注释了
报错信息上说WarmUpCosineDecayScheduler这个类缺少on_test_begin，我看了一下作者重写的这个回调类里确实没有，但是我单独运行这个类检查是没问题的，不知道该怎么改，求解答，非常感谢！

[wusaifei]

你好，这个的原因应该是你的callback的版本没有这个on_test_begin这个，说明keras安装包的版本不对应呢。

[wusaifei]

我这边测试的时候是木有这个报错的

[wusaifei]

reduce_lr = ks.callbacks.ReduceLROnPlateau(monitor='val_acc', factor=0.5, verbose=1, patience=1, min_lr=1e-7)你换成这个也可以的，这个效果和WarmUpCosineDecayScheduler差不多的。把reduce_lr 加到callback里面。

[ghost]

感谢大佬的耐心解答，问题已解决！