microsoft
最后执行的时候出现了一个问题，想问问各位大佬有什么建议
PS C:\Users\20377\OmniParser\OmniParser-master> python gradio_demo.py [2025-03-06 21:11:04,484] [ WARNING] easyocr.py:80 - Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU. [2025-03-06 21:11:04,489] [ WARNING] easyocr.py:251 - Downloading detection model, please wait. This may take several minutes depending upon your network connection. Traceback (most recent call last): File "D:\canda\Lib\urllib\request.py", line 1344, in do_open h.request(req.get_method(), req.selector, req.data, headers, File "D:\canda\Lib\http\client.py", line 1338, in request self._send_request(method, url, body, headers, encode_chunked) File "D:\canda\Lib\http\client.py", line 1384, in _send_request self.endheaders(body, encode_chunked=encode_chunked) File "D:\canda\Lib\http\client.py", line 1333, in endheaders self._send_output(message_body, encode_chunked=encode_chunked) File "D:\canda\Lib\http\client.py", line 1093, in _send_output self.send(msg) File "D:\canda\Lib\http\client.py", line 1037, in send self.connect() File "D:\canda\Lib\http\client.py", line 1472, in connect super().connect() File "D:\canda\Lib\http\client.py", line 1003, in connect self.sock = self._create_connection( ^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\canda\Lib\socket.py", line 865, in create_connection raise exceptions[0] File "D:\canda\Lib\socket.py", line 850, in create_connection sock.connect(sa) ConnectionRefusedError: [WinError 10061] 由于目标计算机积极拒绝，无法连接。
easyocr.py:80 - Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU. 这个应该是torch和cuda驱动不匹配的问题导致gpu没有启用 你本地 python命令行执行：
import torch print(torch.cuda.is_avaliable())
看下是否为True，为false的话就是gpu没有启用，至于下载被拒，可能是网不通或要设置代理
- 你有GPU吗？有的话尝试使用Pytorch gpu的版本 https://github.com/microsoft/OmniParser/issues/258#issuecomment-2727244522
- 第二个报错应该是你的网络有问题，换个网络或者换个梯子。也有可能是因为对方服务器暂时下线了
