-
Dear Ranftl,
Your new small model was converted from Pytorch to TFlite directly. It seems that this method doesn't need converting to onnx and PB first. Can you please elaborate on how to realize i…
-
### Search before asking
- [X] I have searched the YOLOv3 [issues](https://github.com/ultralytics/yolov3/issues) and [discussions](https://github.com/ultralytics/yolov3/discussions) and found no si…
-
Hello, we stumbled upon a numerical issue for below modules while training fp8 quantizated models.
```
ENTRY main {
%p0 = f8e4m3fn[12288,4096]{0,1} parameter(0)
%b = f8e4m3fn[4096,12288]{…
-
### 🚀 The feature, motivation and pitch
LayerNorm starts to be applied to image data on per-channel basis (e.g. in ConvNeXt model).
`torch.nn.LayerNorm` support normalization only on the last se…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussi…
-
### 🐛 Describe the bug
There is a bug in `optimize_for_mobile` with latest torch version and the following nightly versions. Please look at this [discussion](https://discuss.pytorch.org/t/torch-uti…
-
Hi everyone, i have a simple question: if i look at the summary of every model in larq, it looks like that computation for batch normalization has been binarized. I would like to know how this is done…
-
Hi everyone, I'm trying to run the Image Classification example with TF 2.0 and TensorRT 7.
The changes in the API have now made it that the dependency on NETS has been removed but now, it seems that…
-
## Introduction
I am an engineer currently working on 3D model parallelism for transformers. When the tensor model parallelism (https://github.com/huggingface/transformers/pull/13726) is done, I am g…
-
Hi David,
I have trained the tf.keras model on my new images and trying to convert the trained model to coreml model. Till 172/203 are converting fine. But at 173 layer i am getting the below iss…