一个超强 Pytorch 操作！！

import torch

# 创建一个空的张量
empty_tensor = torch.Tensor()

# 从列表创建张量
data = [1, 2, 3, 4]
tensor_from_list = torch.Tensor(data)

import numpy as np

numpy_array = np.array([1, 2, 3, 4])
torch_tensor = torch.from_numpy(numpy_array)

scalar_tensor = torch.tensor(5)
scalar_value = scalar_tensor.item()

original_tensor = torch.randn(2, 3)  # 2x3的随机张量
reshaped_tensor = original_tensor.view(3, 2)  # 将形状改变为3x2

cpu_tensor = torch.randn(3)
gpu_tensor = cpu_tensor.to("cuda")  # 将张量移动到GPU

pytorch_tensor = torch.tensor([1, 2, 3])
numpy_array = pytorch_tensor.numpy()

import torch.nn.functional as F

integer_tensor = torch.tensor([0, 2, 1])
one_hot_encoded = F.one_hot(integer_tensor)

from torch.utils.data import Dataset, DataLoader

class CustomDataset(Dataset):
    def __init__(self, data):
        self.data = data
    
    def __len__(self):
        return len(self.data)
    
    def __getitem__(self, index):
        return self.data[index]

dataset = CustomDataset([1, 2, 3, 4, 5])
dataloader = DataLoader(dataset, batch_size=2, shuffle=True)

import torch
import torchvision.transforms as transforms
from torchvision import models
from PIL import Image
import matplotlib.pyplot as plt

# 下载示例图像
!wget -O example_image.jpg https://pytorch.org/assets/deeplab/deeplab1.jpg

# 定义图像转换
transform = transforms.Compose([
    transforms.Resize((256, 256)),  # 调整大小
    transforms.ToTensor(),           # 转换为张量
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 标准化
])

# 加载并转换图像
image_path = 'example_image.jpg'
image = Image.open(image_path).convert("RGB")
input_tensor = transform(image).unsqueeze(0)  # 添加批次维度

# 加载预训练的DeepLabV3模型
model = models.segmentation.deeplabv3_resnet101(pretrained=True)
model.eval()

# 进行图像分割
with torch.no_grad():
    output = model(input_tensor)['out'][0]
    output_predictions = output.argmax(0)

# 将预测结果转换为彩色图像
def decode_segmap(image, nc=21):
    label_colors = np.array([(0, 0, 0),  # 0: 背景
                             (128, 0, 0), (0, 128, 0), (128, 128, 0), (0, 0, 128), (128, 0, 128),  # 1-5: 物体
                             (0, 128, 128), (128, 128, 128), (64, 0, 0), (192, 0, 0),  # 6-9: 道路
                             (64, 128, 0), (192, 128, 0), (64, 0, 128), (192, 0, 128),  # 10-13: 面部
                             (64, 128, 128), (192, 128, 128), (0, 64, 0), (128, 64, 0),  # 14-17: 植物
                             (0, 192, 0), (128, 192, 0), (0, 64, 128)])  # 18-20: 建筑

    r = np.zeros_like(image).astype(np.uint8)
    g = np.zeros_like(image).astype(np.uint8)
    b = np.zeros_like(image).astype(np.uint8)

    for l in range(0, nc):
        idx = image == l
        r[idx] = label_colors[l, 0]
        g[idx] = label_colors[l, 1]
        b[idx] = label_colors[l, 2]

    rgb = np.stack([r, g, b], axis=2)
    return rgb

# 将预测结果转换为彩色图像
output_rgb = decode_segmap(output_predictions.numpy())

# 可视化原始图像和分割结果
plt.figure(figsize=(12, 6))
plt.subplot(1, 2, 1)
plt.imshow(image)
plt.title('Original Image')

plt.subplot(1, 2, 2)
plt.imshow(output_rgb)
plt.title('Segmentation Result')

plt.show()