A framework to train a ResUNet architecture, quantize, compile and execute it on an FPGA.
-
Updated
Jun 23, 2023 - Jupyter Notebook
A framework to train a ResUNet architecture, quantize, compile and execute it on an FPGA.
Post post-training-quantization (PTQ) method for improving LLMs. Unofficial implementation of https://arxiv.org/abs/2309.02784
Post-training quantization on Nvidia Nemo ASR model
Comprehensive study on the quantization of various CNN models, employing techniques such as Post-Training Quantization and Quantization Aware Training (QAT).
The repository discusses a research work published on MDPI Sensors and provides details about the project.
This sample shows how to convert TensorFlow model to OpenVINO IR model and how to quantize OpenVINO model.
Improved the performance of 8-bit PTQ4DM expecially on FID.
Low-bit (2/4/8/16) Post Training Quantization for ResNet20
Quantization for Object Detection in Tensorflow 2.x
EfficientNetV2 (Efficientnetv2-b2) and quantization int8 and fp32 (QAT and PTQ) on CK+ dataset . fine-tuning, augmentation, solving imbalanced dataset, etc.
Pytorch implementation of our paper accepted by ECCV 2022-- Fine-grained Data Distribution Alignment for Post-Training Quantization
Implementation of EPTQ - an Enhanced Post-Training Quantization algorithm for DNN compression
[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"
Post-Training quantization perfomed on the model trained with CLIC dataset.
Model Quantization with Pytorch, Tensorflow & Larq
Generating tensorrt model using onnx
quantization example for pqt & qat
[CVPR 2024 Highlight] TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
Post-training static quantization using ResNet18 architecture
Add a description, image, and links to the post-training-quantization topic page so that developers can more easily learn about it.
To associate your repository with the post-training-quantization topic, visit your repo's landing page and select "manage topics."