tf.data.Dataset.from_tensor_slices() 详解
生活随笔
收集整理的這篇文章主要介紹了
tf.data.Dataset.from_tensor_slices() 详解
小編覺得挺不錯的,現(xiàn)在分享給大家,幫大家做個參考.
函數(shù)原型:
tf.data.Dataset.from_tensor_slices(tensors, name=None )官網(wǎng)地址:https://www.tensorflow.org/api_docs/python/tf/data/Dataset#from_tensor_slices
功能介紹:
該函數(shù)的作用是接收tensor,對tensor的第一維度進行切分,并返回一個表示該tensor的切片數(shù)據(jù)集
示例講解:
# Slicing a 1D tensor produces scalar tensor elements. import tensorflow as tfdataset = tf.data.Dataset.from_tensor_slices([1, 2, 3]) print(dataset) print(list(dataset.as_numpy_iterator())) <TensorSliceDataset shapes: (), types: tf.int32> [1, 2, 3] # Slicing a 2D tensor produces 1D tensor elements. dataset = tf.data.Dataset.from_tensor_slices([[1, 2], [3, 4]]) print(dataset) print(list(dataset.as_numpy_iterator())) <TensorSliceDataset shapes: (2,), types: tf.int32> [array([1, 2]), array([3, 4])] # Slicing a tuple of 1D tensors produces tuple elements containing # scalar tensors. dataset = tf.data.Dataset.from_tensor_slices(([1, 2], [3, 4], [5, 6])) print(dataset) print(list(dataset.as_numpy_iterator())) <TensorSliceDataset shapes: ((), (), ()), types: (tf.int32, tf.int32, tf.int32)> [(1, 3, 5), (2, 4, 6)] # Dictionary structure is also preserved. dataset = tf.data.Dataset.from_tensor_slices({"a": [1, 2], "b": [3, 4]}) print(dataset) print(list(dataset.as_numpy_iterator())) <TensorSliceDataset shapes: {a: (), b: ()}, types: {a: tf.int32, b: tf.int32}> [{'a': 1, 'b': 3}, {'a': 2, 'b': 4}]實戰(zhàn)案例:
- 深度學習100例-卷積神經(jīng)網(wǎng)絡(CNN)識別驗證碼 | 第12天
總結(jié)
以上是生活随笔為你收集整理的tf.data.Dataset.from_tensor_slices() 详解的全部內(nèi)容,希望文章能夠幫你解決所遇到的問題。
- 上一篇: YOLOv5添加注意力机制 Pytorc
- 下一篇: model.fit() 参数详解【Ten