如何在TensorFlow数据集中播放一个字段

发布于 2025-02-01 05:10:38 字数 1108 浏览 5 评论 0原文

我有一个tf.data.dataset，看起来像这样：

<BatchDataset shapes: ((None, 256, 256, 3), (None,)), types: (tf.float32, tf.int32)>

第二个元素（第1个如果零索引）与标签相对应。我想将第二学期（标签）铸成tf.uint8。

在处理td.data.dataset时，如何使用tf.cast？

类似的问题

如何将tf.int64转换为tf.float32？不适合tf.data.dataset。

repro

来自从scratch ：

curl -O https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_5340.zip
unzip kagglecatsanddogs_5340.zip

TensorFlow〜= 2.4 ：

import tensorflow as tf

ds = tf.keras.preprocessing.image_dataset_from_directory(
    "PetImages", batch_size=32
)
print(ds)

原文

I have a tf.data.Dataset that looks like this:

<BatchDataset shapes: ((None, 256, 256, 3), (None,)), types: (tf.float32, tf.int32)>

The 2nd element (1st if zero indexing) corresponds with a label. I want to cast the 2nd term (labels) to tf.uint8.

How can one use tf.cast when dealing with td.data.Dataset?

Similar Questions

How to convert tf.int64 to tf.float32? is very similar, but is not for a tf.data.Dataset.

Repro

From Image classification from scratch:

curl -O https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_5340.zip
unzip kagglecatsanddogs_5340.zip

Then in Python with tensorflow~=2.4:

import tensorflow as tf

ds = tf.keras.preprocessing.image_dataset_from_directory(
    "PetImages", batch_size=32
)
print(ds)

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

瘫痪情歌 2025-02-08 05:10:38

地图功能可能会有所帮助

a = tf.data.Dataset.from_tensor_slices(np.empty((2,5,3)))
b = tf.data.Dataset.range(5, 8)
c = tf.data.Dataset.zip((a,b))
d = c.batch(1)
d
<BatchDataset shapes: ((None, 5, 3), (None,)), types: (tf.float64, tf.int64)>

# change the dtype of the 2nd arg in the batch from int64 to int8
e = d.map(lambda x,y:(x,tf.cast(y, tf.int8))) 
<MapDataset shapes: ((None, 5, 3), (None,)), types: (tf.float64, tf.int8)>

A map function may help

a = tf.data.Dataset.from_tensor_slices(np.empty((2,5,3)))
b = tf.data.Dataset.range(5, 8)
c = tf.data.Dataset.zip((a,b))
d = c.batch(1)
d
<BatchDataset shapes: ((None, 5, 3), (None,)), types: (tf.float64, tf.int64)>

# change the dtype of the 2nd arg in the batch from int64 to int8
e = d.map(lambda x,y:(x,tf.cast(y, tf.int8))) 
<MapDataset shapes: ((None, 5, 3), (None,)), types: (tf.float64, tf.int8)>

回复收藏 0 原文

~没有更多了~