-
**Describe the bug**
When exporting the YOLOv8s (pruned50-quant, model.pt from sparsezoo) model via the ONNX exporter (sparseml.ultralytics.export_onnx), its performance noticeably decreases compar…
-
Hello author, thank you very much for sharing this project. When I ran decent_q inspect --input_frozen_graph=model_data/yolo.pb during the quantization stage, I got exactly the same results as you, as…
-
This repo. has supported fp16 training and inference for some time.
Running inference at fp16 currently offers the best AP/FPS trade-off but I have found that training at fp16 results in a relative…
-
when trained a model,the accuracy is fairly good,but when convert to pt with torchscript_int8,the Accuracy becomes very poor, I found Quantization aware training ,but now document about it ,can any…
-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.
### Describe the bug
尝试对internlm_xcomposer_vl_7b做量…
-
Hello,
I am new to the world of deep learning. I have successfully converted my trained darknet model to .tflite. However, I don't understand what this means exactly?
`[{'name': 'Identity', 'in…
-
Hii
I am getting a `KeyError` while the quantization process of OpenVINO model
My openVINO model is made of IR of a tensorflow model (pre-trained from tensorflow-hub)
ERROR
```
[/usr/local/lib…
-
## When
- 11.15
## Who :
- 권세중 (sejung.kwon@navercorp.com)
## What
- Title: AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models
- Links: ht…
-
Hi,
I wonder if alpha and delta are layer based (as clained in Trained Ternary Quantization paper) or filter based (like XNOR-Net). I assumed they are filter based because your paper mention n as …
-
Hey there!
Is it possible to do post-training quantitzation with Parseq? I'm looking for ways to speed up inference time. I tried training a parseq-tiny model but lost about 13% absolute val accur…