ryogrid / fx_systrade

FX system trade simulation programs using machine learning methods
https://www.google.com/search?q=%22ryo_grid%22+%22FX%22+%22DQN%22+Deep+Reinforcement+Learning+for+Trading&oq=%22ryo_grid%22+%22FX%22+%22DQN%22+Deep+Reinforcement+Learning+for+Tradingng
89 stars 34 forks source link

Error to run keras_trade.py #3

Open snowsky opened 7 years ago

snowsky commented 7 years ago

Hi there,

When I run the script, I've got this error. Is it the API deprecated? Thanks.

keras_trade.py:346: UserWarning: Update your Dense call to the Keras 2 API: Dense(50, activation="relu", kernel_initializer="uniform", input_shape=(17,)) model.add(Dense(neuro_num,input_shape=(dims,), init='uniform', activation="relu")) Traceback (most recent call last): File "keras_trade.py", line 347, in model.add(BatchNormalization((neuro_num,),input_shape=(dims,))) File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 30, in wrapper args, kwargs, converted = preprocessor(args, kwargs) File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 440, in batchnorm_args_preprocessor raise TypeError('The BatchNormalization layer ' TypeError: The BatchNormalization layer does not accept positional arguments. Use keyword arguments instead.

99thpixel commented 6 years ago

I'm getting the same error.