When running svc onnx, I get the following warnings:
(venv) C:\Users\LXC PC\Desktop\sovits\venv\Scripts>svc onnx -i "C:\Users\LXC PC\Desktop\BackupTraining\sovits\hapiv2\200\G_4800.pth" -o "C:\Users\LXC PC\Desktop\BackupTraining\sovits\hapiv2\200" -c "C:\Users\LXC PC\Desktop\BackupTraining\sovits\hapiv2\config.json"
[15:53:00] INFO [15:53:00] Version: 2.1.2 __main__.py:20
[15:53:02] INFO [15:53:02] Loaded checkpoint 'C:/Users/LXC utils.py:426
PC/Desktop/BackupTraining/sovits/hapiv2/200/G_4800.pth' (iteration 219)
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\utils.py:2033: UserWarning: No
names were found for specified dynamic axes of provided input.Automatically
generated names will be applied to each dynamic axes of input c
warnings.warn(
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\utils.py:2033: UserWarning: No
names were found for specified dynamic axes of provided input.Automatically
generated names will be applied to each dynamic axes of input f0
warnings.warn(
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\utils.py:2033: UserWarning: No
names were found for specified dynamic axes of provided input.Automatically
generated names will be applied to each dynamic axes of input mel2ph
warnings.warn(
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\utils.py:2033: UserWarning: No
names were found for specified dynamic axes of provided input.Automatically
generated names will be applied to each dynamic axes of input uv
warnings.warn(
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\utils.py:2033: UserWarning: No
names were found for specified dynamic axes of provided input.Automatically
generated names will be applied to each dynamic axes of input noise
warnings.warn(
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\so_vits_svc_fork\utils.py:281:
TracerWarning: Converting a tensor to a Python boolean might cause the trace to be
incorrect. We can't record the data flow of Python values, so this value will be
treated as a constant in the future. This means that the trace might not generalize
to other inputs!
assert f0_coarse.max() <= 255 and f0_coarse.min() >= 1, (
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\so_vits_svc_fork\modules\attentions.py:307:
TracerWarning: Converting a tensor to a Python boolean might cause the trace to be
incorrect. We can't record the data flow of Python values, so this value will be
treated as a constant in the future. This means that the trace might not generalize
to other inputs!
t_s == t_t
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\so_vits_svc_fork\modules\attentions.py:369:
TracerWarning: Converting a tensor to a Python boolean might cause the trace to be
incorrect. We can't record the data flow of Python values, so this value will be
treated as a constant in the future. This means that the trace might not generalize
to other inputs!
pad_length = max(length - (self.window_size + 1), 0)
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\so_vits_svc_fork\modules\attentions.py:370:
TracerWarning: Converting a tensor to a Python boolean might cause the trace to be
incorrect. We can't record the data flow of Python values, so this value will be
treated as a constant in the future. This means that the trace might not generalize
to other inputs!
slice_start_position = max((self.window_size + 1) - length, 0)
WARNING [15:53:02] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\so_vits_svc_fork\modules\attentions.py:372:
TracerWarning: Converting a tensor to a Python boolean might cause the trace to be
incorrect. We can't record the data flow of Python values, so this value will be
treated as a constant in the future. This means that the trace might not generalize
to other inputs!
if pad_length > 0:
[15:53:03] WARNING [15:53:03] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\_internal\jit_utils.py:306:
UserWarning: Constant folding - Only steps=1 can be constant folded for opset >= 10
onnx::Slice op. Constant folding not applied. (Triggered internally at
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\jit\passe
s\onnx\constant_fold.cpp:181.)
_C._jit_pass_onnx_node_shape_type_inference(node, params_dict, opset_version)
[15:53:09] WARNING [15:53:09] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\utils.py:689: UserWarning:
Constant folding - Only steps=1 can be constant folded for opset >= 10 onnx::Slice
op. Constant folding not applied. (Triggered internally at
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\jit\passe
s\onnx\constant_fold.cpp:181.)
_C._jit_pass_onnx_graph_shape_type_inference(
[15:53:12] WARNING [15:53:12] C:\Users\LXC warnings.py:109
PC\Desktop\sovits\venv\lib\site-packages\torch\onnx\utils.py:1186: UserWarning:
Constant folding - Only steps=1 can be constant folded for opset >= 10 onnx::Slice
op. Constant folding not applied. (Triggered internally at
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\jit\passe
s\onnx\constant_fold.cpp:181.)
_C._jit_pass_onnx_graph_shape_type_inference(
============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================
Afterwards, I tried using the generated onnx file in MoeSS, but it was not recognized.
When running
svc onnx
, I get the following warnings:Afterwards, I tried using the generated onnx file in MoeSS, but it was not recognized.