AI Rank
EN
← 开源
HasnainRaz

Fast-SRGAN

A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
695
Star
120
Fork
+0
本周
3
贡献者
创建于 2019-10-20 · 更新于 2026-09-01 · 今日第 14879 名
主要开发者
HasnainRazWenheLI

HasnainRaz/Fast-SRGAN 排名第 14,879，有 695 个星标。

同类别比较

HasnainRaz/Fast-SRGAN 排名第 14,879，此处有 8 个同类条目；aleju/mario-ai 排名第 14,883。

同类别比较
名称排名指标
adipandas/multi-object-tracker14,862
语言:
Python
星标数:
697
分叉数:
101
简介:
Multi-object trackers in Python
auroua/InsightFace_TF14,863
语言:
Python
星标数:
697
分叉数:
247
简介:
Insight Face on TensorFlow
tkn-tub/ns3-gym14,870
语言:
C++
星标数:
697
分叉数:
221
简介:
ns3-gym - The Playground for Reinforcement Learning in Networking Research
vecxoz/vecstack14,871
语言:
Python
星标数:
697
分叉数:
79
简介:
Python package for stacking (machine learning technique)
aleju/mario-ai14,883
语言:
Lua
星标数:
695
分叉数:
142
简介:
Playing Mario with Deep Reinforcement Learning
mv-lab/swin2sr14,889
语言:
Python
星标数:
695
分叉数:
83
简介:
[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr
soobinseo/Transformer-TTS14,890
语言:
Python
星标数:
695
分叉数:
139
简介:
A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
flink-extended/dl-on-flink14,901
语言:
Java
星标数:
694
分叉数:
196
简介:
Deep Learning on Flink aims to integrate Flink and deep learning frameworks (e.g. TensorFlow, PyTorch, etc) to enable distributed deep learning training and inference on a Flink cluster.
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
星标数695
分叉数120
贡献者3
创建日期2019-10-20
更新日期2026-09-01
1 天星标数0
7 天星标数0
排名14,879
上次排名14,717
排名变化-162
7 天星标排名14,697
上次 7 天星标排名14,708
7 天星标排名变化11
总星标排名14,956
上次总星标排名14,930
总星标排名变化-26
README 摘录

Fast-SRGAN The goal of this repository is to enable real time super resolution for upsampling low resolution videos. Currently, the design follows the SR-GAN architecture. For speed, the upsampling is done through pixel shuffle. The training setup looks like the following diagram: Speed Benchmarks The following runtimes/fps are obtained by averaging runtimes over 800 frames. 01 | 82 | | 180x320 | 720x1080 (720p) | 0. 04 | 27 | We see it's possible to upsample to 720p at around 30fps. Requirements This was

tested on Python 3. To install the required packages, use the provided Pipfile: Pre-trained Model A pretrained generator model on the DIV2k dataset is provided in the 'models' directory. It uses 8 residual blocks, with 64 filters in every layer of the generator. To try out the provided pretrained model on your own images, run the following: Training To train, simply edit the config file in the folder with your settings, and then launch the training with: You can

also change the config parameters from the command line. The following will run training with a of 32, a generator with 12 residual blocks, and a path to the image directory . This is powered by , which means all the parameters in the config are editable via the CLI. Model checkpoints and training summaries are saved in tensorboard. To monitor training progress, open up tensorboard by pointing it to the directory that will be created when you start training. Samples Following

are some results from the provided trained model. Left shows the low res image, after 4x bicubic upsampling. Right is the actual high resolution image. The following shows images upsampled 4x by bicubic interpolation, the pretrained model from this repository and the original high resolution image as a comparison Contributing If you have ideas on improving model performance, adding metrics, or any other changes, please make a pull request or open an issue. I'd be happy to accept any contributions

.

常见问题

记录了多少星标和分叉？

HasnainRaz/Fast-SRGAN 有 695 个星标和 120 个分叉。

仓库排名是多少？

HasnainRaz/Fast-SRGAN 排名第 14,879。

记录的语言和类别是什么？

HasnainRaz/Fast-SRGAN 有 695 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

HasnainRaz/Fast-SRGAN 与 aleju/mario-ai 比较，后者排名第 14,883，有 695 个星标。

README

Fast-SRGAN

The goal of this repository is to enable real time super resolution for upsampling low resolution videos. Currently, the design follows the SR-GAN architecture. For speed, the upsampling is done through pixel shuffle.

The training setup looks like the following diagram:

Speed Benchmarks

The following runtimes/fps are obtained by averaging runtimes over 800 frames. Measured on MPS (MacBook M1 Pro GPU).

Input Image Size Output Size Time (s) FPS
90x160 360x640 (360p) 0.01 82
180x320 720x1080 (720p) 0.04 27

We see it's possible to upsample to 720p at around 30fps.

Requirements

This was tested on Python 3.10. To install the required packages, use the provided Pipfile:

pip install pipenv --upgrade
pipenv install --system --deploy

Pre-trained Model

A pretrained generator model on the DIV2k dataset is provided in the 'models' directory. It uses 8 residual blocks, with 64 filters in every layer of the generator.

To try out the provided pretrained model on your own images, run the following:

python inference.py --image_dir 'path/to/your/image/directory' --output_dir 'path/to/save/super/resolution/images'

Training

To train, simply edit the config file in the folder configs/config.yaml with your settings, and then launch the training with:

python train.py

You can also change the config parameters from the command line. The following will run training with a batch_size of 32, a generator with 12 residual blocks, and a path to the image directory /path/to/image/dataset.

python train.py data.image_dir="/path/to/image/dataset" training.batch_size=32 generator.n_layers=12

This is powered by hydra, which means all the parameters in the config are editable via the CLI.

Model checkpoints and training summaries are saved in tensorboard. To monitor training progress, open up tensorboard by pointing it to the outputs directory that will be created when you start training.

Samples

Following are some results from the provided trained model. Left shows the low res image, after 4x bicubic upsampling. Middle is the output of the model. Right is the actual high resolution image.

The following shows images upsampled 4x by bicubic interpolation, the pretrained model from this repository and the original high resolution image as a comparison

Contributing

If you have ideas on improving model performance, adding metrics, or any other changes, please make a pull request or open an issue. I'd be happy to accept any contributions.

排名相邻
同类项目