-
Hi, I want to measure the quantization noise during inference time when the rounding mode is put to 'stochastic'. However, I am having a hard time constructing such stochastic noise, as the outputs of…
-
## Description
When I use TensorRT for int8 quantization, I always encounter the accuracy fallback to fp32. The trt.BuilderFlag.OBEY_PRECISION_CONSTRAINTS parameter does not solve the issue. W…
-
Hello Maurice,
i'm a newbie to deep learning. I studied your paper and am trying to improve on it as a small project. If possible, i would appreciate it to hear from your on some ideas to improve on …
-
### 🐛 Describe the bug
Hi, I'm trying to perform XNNPACK quantization for PyTorch model. I have successfully delegate the model to xnnpACK and try to perform model quantization as follows:
```python…
-
I try to convert a simple network with QuantizeLinear/DequantizeLinear but it fails.
The network is very simple that it only contains one tensor as input. Its definition could be found in test of p…
-
Currently, we supports only `DivideBy255` preprocessor. However, internally, we've prepared `PerImageStandardization`. @yasumura-lm san mentioned that sometimes this preprocessing method is is very ef…
-
Hi
Firstly, I appreciate you for this project. It seems you haven't updated your code since four years ago. Some errors occur for
`python3 main_binary.py -a mobilenet --mobilenet_width 1.0 --mobil…
-
IndexError Traceback (most recent call last)
/home/chenwz/code/pycharm/test2.ipynb Cell 6' in ()
[2](vscode-notebook-cell://ssh-remote%2Bchenwz/home/chenwz/code/…
-
When using a network that splits the tensor at some point in the network into two pieces, I run into a problem. The `torch.split` operator is not supported, so I rewrote it using two slices:
```
b =…
-
Hello there,
I just noticed that the compiler's help text does not comply with the actual implementation (see sw/umd/apps/compiler/main.cpp).
The help text is as follows:
```
Usage: ./nvdla_c…