在运行工具箱合成声音时出现了这个提示是怎么回事呀

[7zyz7]

Traceback (most recent call last): File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\flask\app.py", line 2073, in wsgi_app response = self.full_dispatch_request() File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\flask\app.py", line 1518, in full_dispatch_request rv = self.handle_user_exception(e) File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\flask_restx\api.py", line 672, in error_router return original_handler(e) File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\flask\app.py", line 1516, in full_dispatch_request rv = self.dispatch_request() File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\flask\app.py", line 1502, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(req.view_args) File "D:\PythonProject\Pytorch\MockingBird_main\web__init__.py", line 108, in synthesize specs = current_synt.synthesize_spectrograms(texts, embeds) File "D:\PythonProject\Pytorch\MockingBird_main\synthesizer\inference.py", line 128, in synthesizespectrograms , mels, alignments = self._model.generate(chars, speaker_embeddings, style_idx=style_idx, min_stop_token=min_stop_token, steps=steps) File "D:\PythonProject\Pytorch\MockingBird_main\synthesizer\models\tacotron.py", line 448, in generate encoder_seq = self.encoder(x, speaker_embedding) File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl return forward_call(*input, *kwargs) File "D:\PythonProject\Pytorch\MockingBird_main\synthesizer\models\tacotron.py", line 41, in forward x = self.cbhg(x) File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl return forward_call(input, kwargs) File "D:\PythonProject\Pytorch\MockingBird_main\synthesizer\models\tacotron.py", line 138, in forward c = conv(x) # Convolution File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl return forward_call(*input, *kwargs) File "D:\PythonProject\Pytorch\MockingBird_main\synthesizer\models\tacotron.py", line 84, in forward x = self.conv(x) File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl return forward_call(input, **kwargs) File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\torch\nn\modules\conv.py", line 301, in forward return self._conv_forward(input, self.weight, self.bias) File "D:\ProgramData\Anaconda3\envs\Pytorch\lib\site-packages\torch\nn\modules\conv.py", line 298, in _conv_forward self.padding, self.dilation, self.groups) RuntimeError: Unable to find a valid cuDNN algorithm to run convolution

直接用的大佬的模型

[babysor]

pytorch安装正常了吗？显卡是不是不支持cuda

[7zyz7]

应该是没有问题，之前自己训练模型的时候也用的cuda训练成功了，这次不知道为什么

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年3月12日(星期六) 晚上7:12 收件人: @.>; 抄送: "Yuzhu @.>; @.>; 主题: Re: [babysor/MockingBird] 在运行工具箱合成声音时出现了这个提示是怎么回事呀 (Issue #450)

pytorch安装正常了吗？显卡是不是不支持cuda

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: @.***>

[babysor]

看报错，是pytorch出了问题，每次必现吗？

[7zyz7]

不是欸，使用了您发布的老版本就没有问题，我运行新版本会报这个错误

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年3月12日(星期六) 晚上7:29 收件人: @.>; 抄送: "Yuzhu @.>; @.>; 主题: Re: [babysor/MockingBird] 在运行工具箱合成声音时出现了这个提示是怎么回事呀 (Issue #450)

看报错，是pytorch出了问题，每次必现吗？

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: @.***>