批处理是为训练序列模型格式化数据的一组工具
batching的Python项目详细描述
批处理
批处理是为训练序列模型格式化数据的一组工具。
安装
$ pip install batching
示例用法
示例脚本存在于SpP.Py
# Metadata for batch info - including batch IDs and mappings to storage resouces like filenamesstorage_meta=StorageMeta(validation_split=0.2)# Storage for batch data - Memory, Files, S3storage=BatchStorageMemory(storage_meta)# Create batches - configuration contains feature names, windowing config, timeseries spacingbatch_generator=Builder(storage,feature_set,look_back,look_forward,batch_seconds,batch_size=128)batch_generator.generate_and_save_batches(list_of_dataframes)# Generator for feeding batches to training - tf.keras.model.fit_generatortrain_generator=BatchGenerator(storage)validation_generator=BatchGenerator(storage,is_validation=True)model=tf.keras.Sequential()model.add(tf.keras.layers.Dense(1,activation='sigmoid')model.compile(loss=tf.keras.losses.binary_crossentropy,optimizer=tf.keras.optimizers.Adam(),metrics=['accuracy'])model.fit_generator(train_generator,validation_data=validation_generator,epochs=epochs)
许可证
- MIT license
- 版权所有2015）FVCproductions。
欢迎加入QQ群-->： 979659372
