如何在tensoflow中将float32 tif图像解码为float32张量? [英] How to decode float32 tif images to float32 tensor in tensoflow?

问题描述

我有一组 tif 格式的 float32 数据类型的输入图像(rgb)和图像目标(灰度).是否可以在 tensorflow 中将它们解码为 float32 张量?

I have a sets of input images (rgb) and image targets (grayscale) in float32 data type by tif format. Is it possible to decode them into float32 tensor in tensorflow?

推荐答案

在撰写此评论时 tfio.experimental.image.decode_tiff().然而，输出格式是 uint8 而不是 float32.

At the time of writing this comment tfio.experimental.image.decode_tiff(). Nevertheless the output format is uint8 rather than float32.

我建议您使用 OpenCV 或 Pillow 阅读图像.

I suggest that you read the image with OpenCV or Pillow.

例如使用 OpenCV:

E.g with OpenCV:

import cv2
import tensorflow as tf
image = cv2.imread('image.tif')
tf_tensor = tf.convert_to_tensor(image, dtype=float32)

这篇关于如何在tensoflow中将float32 tif图像解码为float32张量?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！