Cdfi: Compression-driven network design for frame interpolation

T Ding, L Liang, Z Zhu… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
DNN-based frame interpolation--that generates the intermediate frames given two
consecutive frames--typically relies on heavy model architectures with a huge number of …

Otov2: Automatic, generic, user-friendly

T Chen, L Liang, T Ding, Z Zhu, I Zharkov - ar**_YOLOv4-Tiny_on_FPGA-Based_DNN_Accelerator_by_Using_Dynamic_Fixed-Point_Method/links/62a86840a3fe3e3df8776ecb/Map**-YOLOv4-Tiny-on-FPGA-Based-DNN-Accelerator-by-Using-Dynamic-Fixed-Point-Method.pdf" data-clk="hl=sk&sa=T&oi=gga&ct=gga&cd=8&d=7733090446757097527&ei=r1rCZ9L-ONq16rQPjs6rqQ8" data-clk-atid="N3DsJsp0UWsJ" target="_blank">[PDF] researchgate.net

Map** yolov4-tiny on fpga-based dnn accelerator by using dynamic fixed-point method

P Li, C Che - 2021 12th International Symposium on Parallel …, 2021 - ieeexplore.ieee.org
In the past few decades, with the large-scale application of deep learning technology, the
neural network inference speed problem is becoming more and more severe, especially in …

Onnxpruner: Onnx-based general model pruning adapter

D Ren, W Li, T Ding, L Wang, Q Fan, J Huo… - ar** new algorithms and
improving upon benchmarks. However, the practical application of these algorithms across …