[pytorch] csv转tensor，tensor转图片

最新推荐文章于 2024-09-16 22:24:15 发布

原创最新推荐文章于 2024-09-16 22:24:15 发布 · 1.1k 阅读

6 ·

CC 4.0 BY-SA版权

文章标签：

#pytorch #深度学习 #python #数据分析 #计算机视觉

该博客介绍了如何将CSV数据转换为PyTorch张量，并展示了将张量转换为PIL图像、在TensorBoard中展示以及保存为指定格式图片的流程。主要涉及数据处理和深度学习的辅助工具使用。

部署运行你感兴趣的模型镜像

csv转tensor

def csv_to_tensor(csvDate):
    df = pd.read_csv(csvDate)
    array = np.array(df)
    tensor = torch.tensor(array, dtype=torch.float64)
    return tensor

tensor转PIL

def tensor_to_PIL(tensor):
    unloader = transforms.ToPILImage()
    image = tensor.cpu().clone()
    image = image.squeeze(0)
    image = unloader(image)
    return image

在tensorboard中展示

def show_in_tensorboard(tensor):
    if tensor.dim() < 3:
        tensor = tensor.unsqueeze(0)
    writer = SummaryWriter("logs")
    writer.add_image("Tensor_img", tensor)
    writer.close()
    return tensor

保存为指定格式的图片

def save_as_img(tensor, img_name, img_type):
    tensor_to_PIL(tensor).save(img_name + '.' + img_type)

操作实例：

import numpy as np
import pandas as pd
import torch
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

csvDateSet = './00000.csv'


def csv_to_tensor(csvDate):
    df = pd.read_csv(csvDate)
    array = np.array(df)
    tensor = torch.tensor(array, dtype=torch.float64)
    return tensor


def tensor_to_PIL(tensor):
    unloader = transforms.ToPILImage()
    image = tensor.cpu().clone()
    image = image.squeeze(0)
    image = unloader(image)
    return image


def show_in_tensorboard(tensor):
    if tensor.dim() < 3:
        tensor = tensor.unsqueeze(0)
    writer = SummaryWriter("logs")
    writer.add_image("Tensor_img", tensor)
    writer.close()
    return tensor


def save_as_img(tensor, img_name, img_type):
    tensor_to_PIL(tensor).save(img_name + '.' + img_type)


if __name__ == '__main__':
    my_tensor = csv_to_tensor(csvDateSet)
    save_as_img(my_tensor, 'example', 'jpg')
    my_tensor = show_in_tensorboard(my_tensor)

您可能感兴趣的与本文相关的镜像

PyTorch 2.5

PyTorch

Cuda

PyTorch 是一个开源的 Python 机器学习库，基于 Torch 库，底层由 C++ 实现，应用于人工智能领域，如计算机视觉和自然语言处理