Segmentation fault (core dumped)

[lisi-github]

---

when i call export_and_get_onnx_model，some errors have occurred
my gpu is v100，softwares are fastt5(0.1.4)、python(3.8.0)、torch(2.0.0)、onnx(1.13.1)、onnxruntime(1.10.0)

---

the detailed error information is as follows：
In-place op on output of tensor.shape. See https://pytorch.org/docs/master/onnx.html#avoid-inplace-operations-when-using-tensor-shape-in-tracing-mode
In-place op on output of tensor.shape. See https://pytorch.org/docs/master/onnx.html#avoid-inplace-operations-when-using-tensor-shape-in-tracing-mode
============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Exporting to onnx... |########## | 1/3============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Exporting to onnx... |##################### | 2/3============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Exporting to onnx... |################################| 3/3
Quantizing... |################################| 3/3
Setting up onnx model...
Traceback (most recent call last):
File "t5_onnx.py", line 8, in
model = export_and_get_onnx_model("/root/t5_correct/t5/", "/root/t5_correct/t5_onnx/")
File "/root/.local/conda/envs/py38/lib/python3.8/site-packages/fastT5/onnx_models.py", line 223, in export_and_get_onnx_model
Segmentation fault (core dumped)

[zzzhaoguziji]

I solved the problem like this

[lisi-github]

thank you,but my problem is such as this:
when i run this code [model = export_and_get_onnx_model("/root/t5_correct/t5/", "/root/t5_correct/t5_onnx/")] for gettig a onnx model, the Segmentation fault occurred

============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Exporting to onnx... |########## | 1/3============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Exporting to onnx... |##################### | 2/3============= Diagnostic Run torch.onnx.export version 2.0.0+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Exporting to onnx... |################################| 3/3
Quantizing... |################################| 3/3
Setting up onnx model...
Traceback (most recent call last):
File "t5_onnx.py", line 7, in
model = export_and_get_onnx_model("/root/t5_correct/t5/", "/root/t5_correct/t5_onnx/")
File "/root/.local/conda/envs/py38/lib/python3.8/site-packages/fastT5/onnx_models.py", line 223, in export_and_get_onnx_model
Segmentation fault (core dumped)

[zzzhaoguziji]

This should be the same

[zzzhaoguziji]

You should change n_threads to your CPU cores

[lisi-github]

I understand. Thank you very much