New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Jump to bottom

SqueezeLayer has invalid input axes when convert lstm onnx to tnn model #1960

Open

Haibit opened this issue Sep 20, 2023 · 0 comments

Haibit commented Sep 20, 2023

1. 使用环境（environment）

OS: Docker
OS Version:

2. Github版本

branch：master
commit(optional):

3. 详细描述bug 情况 (Describe the bug)
A clear and concise description of what the bug is.

issue type: 编译问题（Build failed）/ 模型转换失败（converter failed）/ 模型不对齐（model misalignment）
original model： Caffe/ONNX/TensorFlow/TensorFlowLite
（如果可以的话，请上传原始的模型文件）

3层LSTM结构，将隐藏层拿出来保存用作序列模型。转换TNN的时候报错：ConstFolder Init Error: code: 0x1000 msg: SqueezeLayer has invalid input axes

模型文件见：
链接：https://pan.baidu.com/s/1ATR6mtytKvv-60ZN2IJ5-g
提取码：2fwm

4. 日志（Log）

将日志粘贴在这里
Paste log here or pastebin

日志见：
链接：https://pan.baidu.com/s/1ATR6mtytKvv-60ZN2IJ5-g
提取码：2fwm

5. 截图（Screenshots）
If applicable, add screenshots to help explain your problem.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment