-
When the model uses blfloat16 ops, the optimizer fails with the following. We should handle custom types form onnx in `_constant_folding`
```pytb
Traceback (most recent call last):
File "/works…
-
Click to expand!
### Issue Type
Bug
### Source
binary
### Tensorflow Version
2.6
### Custom Code
Yes
### OS Platform and Distribution
Ubuntu 18.04
### Mobile device…
-
Hello
I'm trying to use the bert_mha_layernorm_fuse() function in the examples.py
The problem is when I'm trying to infer the fused model I'm getting a dtype mismatch error
After a little debug…
-
### 🐛 Describe the bug
I've found that the output of the wav2vec2 pipeline model is bugged, and changes depending on the zero-padding used in batch preprocessing, a simple example Is as follows:
…
-
This issue is to discuss issues and possible improvements to enhance the type safety of the C++ code, and thereby increase the maintainability.
The main issue that I can see is the int `dtype`. Th…
-
Hello! I have recently been trying to train my mesh to ground truth by using the normals of some images in the COLMAP dataset, specifically, the camera information that provides each view in the datas…
-
### 🐛 Describe the bug
Dear all,
We seemly found a bug in nn.linear forwarding, here is a minimal example:
```python
# import
import torch
import time
# Set input size, output size, an…
-
Hi~
I meet a question RuntimeError: The size of tensor a (212) must match the size of tensor b (0) at non-singleton dimension 0，when I try to run code imputer.fit() and the dataset I used is heart.cs…
-
Guys, this is a very general comment and FYI...
To some extent you guys seem to be viewing NestedTensor as a generic ragged-tensor data structure, similar to TensorFlow's RaggedTensor. I understan…
-
### Describe the issue
we are using onnxruntime-web and want to know if there is a configuration to customize the nn inference location. the method now is getting from the root of the app build but w…