python3.9 dict获取所有key

可以使用Python3.9的字典方法keys()来获取所有的key，例如：

my_dict = {'name': 'Tom', 'age': 25, 'gender': 'male'}
all_keys = my_dict.keys()
print(all_keys)

输出结果为：

dict_keys(['name', 'age', 'gender'])

相关问题

python3.9 dict元素访问

你可以使用字典的键来访问元素，例如：dict_name[key]。如果键不存在，会抛出KeyError异常。你也可以使用get()方法来访问元素，如果键不存在，会返回None或者指定的默认值。例如：dict_name.get(key, default_value)。

>> %Run first2.py Traceback (most recent call last): File "/home/pi/Desktop/first2.py", line 74, in <module> model.load_state_dict(torch.load(r"/home/pi/Desktop/epoch50.pkl"))#模型位置 File "/home/pi/.local/lib/python3.9/site-packages/torch/serialization.py", line 592, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "/home/pi/.local/lib/python3.9/site-packages/torch/serialization.py", line 851, in _load result = unpickler.load() File "/home/pi/.local/lib/python3.9/site-packages/torch/serialization.py", line 843, in persistent_load load_tensor(data_type, size, key, _maybe_decode_ascii(location)) File "/home/pi/.local/lib/python3.9/site-packages/torch/serialization.py", line 832, in load_tensor loaded_storages[key] = restore_location(storage, location) File "/home/pi/.local/lib/python3.9/site-packages/torch/serialization.py", line 175, in default_restore_location result = fn(storage, location) File "/home/pi/.local/lib/python3.9/site-packages/torch/serialization.py", line 151, in _cuda_deserialize device = validate_cuda_device(location) File "/home/pi/.local/lib/python3.9/site-packages/torch/serialization.py", line 135, in validate_cuda_device raise RuntimeError('Attempting to deserialize object on a CUDA ' 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.

这个错误是因为你的代码尝试在CUDA设备上加载模型参数，但是检测到没有可用的CUDA设备。如果你在一个只有CPU的机器上运行代码，请使用`torch.load`函数的`map_location`参数将模型参数映射到CPU上。你可以尝试修改代码如下：

model.load_state_dict(torch.load(r"/home/pi/Desktop/epoch50.pkl", map_location=torch.device('cpu')))

这样就能够将模型参数加载到CPU上了。希望对你有帮助！如果还有其他问题，请随时提问。