We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Convert model with the latest version of ncnn with pytorch==0.4.1 on Mac:
ncnn
pytorch==0.4.1
pytorch -> onnx -> ncnn
A simple RNN model,
rnn = nn.RNN(1, 2, 2) input = torch.randn(5, 3, 1) h0 = torch.randn(2, 3, 2) output, hn = rnn(input, h0) torch.onnx.export(rnn, input, 'rnn.onnx')
use onnx2ncnn tool:
./onnx2ncnn rnn.onnx
Errors:
Unsqueeze not supported yet! # axes 7 Unsqueeze not supported yet! # axes 7 Unsqueeze not supported yet! # axes 7 Shape not supported yet! Gather not supported yet! Unsqueeze not supported yet! # axes 7 Unsqueeze not supported yet! # axes 7 ConstantFill not supported yet! # input_as_shape=1 RNN not supported yet! # activations 8 # hidden_size=2 Squeeze not supported yet! # axes 7 Unsqueeze not supported yet! # axes 7 Unsqueeze not supported yet! # axes 7 Unsqueeze not supported yet! # axes 7 Shape not supported yet! Gather not supported yet! Unsqueeze not supported yet! # axes 7 Unsqueeze not supported yet! # axes 7 ConstantFill not supported yet! # input_as_shape=1 RNN not supported yet! # activations 8 # hidden_size=2 Squeeze not supported yet! # axes 7
Anybody has tried to convert the pytorch RNN model before?
The text was updated successfully, but these errors were encountered:
not support yet, confirmed by the author.
Sorry, something went wrong.
pytorch mobilenetv1-ssd: pytorch -> onnx -> ncnn Unsqueeze not supported yet! [110/1610]
Shape not supported yet! Gather not supported yet!
Unsqueeze not supported yet!
No branches or pull requests
Convert model with the latest version of
ncnn
withpytorch==0.4.1
on Mac:pytorch -> onnx -> ncnn
A simple RNN model,
use onnx2ncnn tool:
./onnx2ncnn rnn.onnx
Errors:
Anybody has tried to convert the pytorch RNN model before?
The text was updated successfully, but these errors were encountered: