A wrapper for Keras models
Project description
ModelManager
Wrapper for keras models to ensure logging and reproducibility
import keras
from keras.models import Sequential
from ModelManager import ModelManager
# Create some simple model
my_model = Sequential()
my_model.add(Dense(2, input_dim=1, activation='relu'))
my_model.add(Dense(1, activation='sigmoid'))
my_model.compile(optimizer=keras.optimizers.Adam(learning_rate=0.01), loss='categorical_crossentropy')
# Some data
x = [1, 2, 3, 4, 5]
y = [1, 2, 3, 4, 5]
mm = ModelManager("some/path", model=my_model, save_history=True, save_weights=True, save_model=True)
mm.fit(x=x, y=y, batch_size=1, epochs=3)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for KerasModelManager-0.0.8-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | dea7e907159f8d4e0cf3ba1aaaf8008e8bb981dfe6ded147d5acb3d8fc036274 |
|
MD5 | dfbe9a72a3d5d05a3fc20d322080122a |
|
BLAKE2b-256 | adb03a1ca1fdb8e24a2f57d9c0c7d785aa9dbbc6e9c57228f01672b99ae276dc |