Metadata-Version: 2.1
Name: keras_rnadam
Version: 0.2.0
Summary: Rectified Nadam implemented in Keras
Home-page: https://github.com/niley1nov/keras_rnadam/archive/0.2.0.tar.gz
Author: niley1nov
Author-email: nilaysharma1nov@gmail.com
License: MIT
Description: # Keras RNAdam
        
        use of nesterov accelerated geadient instead of momentum in rectified-adam
        
        ## Install
        
        ```bash
        pip install keras_rnadam
        ```
        
        ## Usage
        
        ```python
        import keras
        import numpy as np
        from keras_rnadam import RNAdam
        
        # Build toy model with RNAdam optimizer
        model = keras.models.Sequential()
        model.add(keras.layers.Dense(input_shape=(17,), units=3))
        model.compile(RNAdam(), loss='mse')
        
        # Generate toy data
        x = np.random.standard_normal((4096 * 30, 17))
        w = np.random.standard_normal((17, 3))
        y = np.dot(x, w)
        
        # Fit
        model.fit(x, y, epochs=5)
        ```
        
        ### Use Warmup
        
        ```python
        from keras_nradam import RNAdam
        RNAdam(total_step=10000, warmup_proportion=0.1, min_lr=1e-5)
        ```
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3.7
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
