-
Hi all,
I would like to know whether the nn_quantizer.py and code_gen.py works for all caffe models with specified restrictions.
As an example:
1. In NXP mnist example, they are mentioning lik…
-
Hello, I am using a [quantize scale](https://vega.github.io/vega/docs/scales/#quantize) over a color range. In some cases, I want the outermost quantized segment values to be at the outermost of the r…
-
## Description
yolov5s base pytorch-quantization
reference https://github.com/maggiez0138/yolov5_quant_sample
onnx->fp16 3ms
qat->onnx->int8 4ms
why? please tell me，thanks.
[onnx fil…
-
Two strategies to auto-quantization:
1. The user provides the tempo of the track in BPM using a tempo app on their phone which allows you to tap out the tempo you're playing in
2. An AI that finds t…
-
### 🚀 The feature
Add quantization support for `BackboneWithFPN`.
### Motivation, pitch
Currently, it is possible to use `from torchvision.models.detection.backbone_utils.resnet_fpn_backbone/Backbo…
-
## Description
For the NativeMemoryCacheManager, we allow users to enable an "expirary" time setting, so that cache entries that arent touched for some duration, get marked as expired and are then …
-
The graph optimizations should not change the numerical behavior of a graph before/after transformation.
Some graph optimizations for quantized operations change the numerical behavior:
1. Merging m…
-
## 🐛 Bug
Scalar Quantization does not seem to work on a pretrained RoBERTa model.
### To Reproduce
Script to run without quantization
TOTAL_NUM_UPDATES=2036
WARMUP_UPDATES=122
LR=2e-05
…
-
## 🐛 Bug
I followed instructions to use the Iterative Product Quantization provided here: (https://github.com/pytorch/fairseq/tree/master/examples/quant_noise)
I succeeded to create a transformer …
-
When lowering for example a 1x1 Conv to FullyConnected the weights will have Reshape and Transpose attached to them.
If this FullyConnected is desired to be further quantized rowwise the quantization…