autonomio / talos

Hyperparameter Experiments with TensorFlow and Keras
https://autonom.io
MIT License
1.62k stars 268 forks source link

TypeError: __call__() takes 2 positional arguments but 6 were given #430

Closed Dishant-P closed 4 years ago

Dishant-P commented 4 years ago

I am trying to tune hyperparameters of a custom keras model, but always get this error. Below is the param_grid I am using: p = {'lr': (0.5, 5, 10), 'first_neuron':[4, 8, 16, 32, 64], 'hidden_layers':[0, 1, 2], 'batch_size': (10,30,64,128,256), 'epochs': [10,20,40,80,200,500], 'dropout': (0, 0.5, 5), 'weight_regulizer':[None], 'emb_output_dims': [None], 'shape':['brick','long_funnel'], 'optimizer': ['Adam', 'Nadam', 'RMSprop'], 'losses': ['logcosh', 'binary_crossentropy'], 'activation':['relu', 'elu'], 'last_activation': ['sigmoid']}

github-actions[bot] commented 4 years ago

Welcome to Talos community! Thanks so much for creating your first issue :)

mikkokotila commented 4 years ago

Can you share the actual code you are trying to execute.

Dishant-P commented 4 years ago

The error didn't persist, it was just due to a problem with the parameters written, it follows with an index out of range error, but it was solved using the other thread that has already been discussed upon. Thanks anyway.