PyTorch CUDA设备不可用错误的解决方案

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
已中止 (核心已转储)

import torch

# 方法1：直接指定CPU设备
model = torch.load('model.pth', map_location=torch.device('cpu'))

# 方法2：使用字符串指定
model = torch.load('model.pth', map_location='cpu')

# 方法3：使用lambda函数
model = torch.load('model.pth', map_location=lambda storage, loc: storage.cpu())

nvidia-smi

import torch
print(f"PyTorch版本: {torch.__version__}")
print(f"CUDA可用: {torch.cuda.is_available()}")
print(f"CUDA版本: {torch.version.cuda}")

# 安装支持CUDA的PyTorch
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
# 或使用conda
conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia

# 保存模型时使用state_dict
torch.save(model.state_dict(), 'model_weights.pth')

# 加载模型时指定设备
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.load_state_dict(torch.load('model_weights.pth', map_location=device))

# AMD显卡不支持CUDA，使用CPU
device = torch.device('cpu')

# Apple M系列芯片使用MPS加速
if torch.backends.mps.is_available():
    device = torch.device('mps')
else:
    device = torch.device('cpu')

import torch
import os

def load_model_safely(model_path, model_class, **kwargs):
    """
    安全加载模型，自动处理设备兼容性问题
    """
    # 检测可用设备
    if torch.cuda.is_available():
        device = torch.device('cuda')
        print("✅ 检测到CUDA设备，使用GPU加速")
    elif hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
        device = torch.device('mps')
        print("✅ 检测到Apple M系列芯片，使用MPS加速")
    else:
        device = torch.device('cpu')
        print("💻 未检测到GPU设备，使用CPU")
    
    # 创建模型实例
    model = model_class(**kwargs)
    
    try:
        # 尝试加载state_dict
        state_dict = torch.load(model_path, map_location=device)
        
        # 处理checkpoint格式
        if isinstance(state_dict, dict) and 'model_state_dict' in state_dict:
            state_dict = state_dict['model_state_dict']
        
        # 处理多GPU训练的模型
        if list(state_dict.keys())[0].startswith('module.'):
            state_dict = {k.replace('module.', ''): v for k, v in state_dict.items()}
        
        model.load_state_dict(state_dict)
        model = model.to(device)
        model.eval()
        
        print(f"✅ 模型成功加载到 {device}")
        return model, device
        
    except Exception as e:
        print(f"❌ 模型加载失败: {str(e)}")
        raise

# 使用示例
if __name__ == "__main__":
    # 假设你有一个模型类MyModel
    # model, device = load_model_safely('model.pth', MyModel, num_classes=10)
    pass

torch.save(model.state_dict(), 'model_weights.pth')

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.load_state_dict(torch.load('model_weights.pth', map_location=device))

print(f"PyTorch版本: {torch.__version__}")
print(f"CUDA可用: {torch.cuda.is_available()}")
print(f"GPU数量: {torch.cuda.device_count()}")
if torch.cuda.is_available():
    print(f"GPU名称: {torch.cuda.get_device_name(0)}")