All Projects → Kazuhito00 → AnimeGANv2-ONNX-Sample

Kazuhito00 / AnimeGANv2-ONNX-Sample

Licence: MIT license
「PyTorch Implementation of AnimeGANv2」のPythonでのONNX推論サンプル

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to AnimeGANv2-ONNX-Sample

AnimeGANv3
Use AnimeGANv3 to make your own animation works, including turning photos or videos into anime.
Stars: ✭ 878 (+1525.93%)
Mutual labels:  onnx, animeganv2
kinference
Running ONNX models in vanilla Kotlin
Stars: ✭ 70 (+29.63%)
Mutual labels:  onnx
Torrent-To-Google-Drive-Downloader
Simple notebook to stream torrent files to Google Drive using Google Colab and python3.
Stars: ✭ 256 (+374.07%)
Mutual labels:  colaboratory
deepvac
PyTorch Project Specification.
Stars: ✭ 507 (+838.89%)
Mutual labels:  onnx
Tengine-Convert-Tools
Tengine Convert Tool supports converting multi framworks' models into tmfile that suitable for Tengine-Lite AI framework.
Stars: ✭ 89 (+64.81%)
Mutual labels:  onnx
torch-model-compression
针对pytorch模型的自动化模型结构分析和修改工具集,包含自动分析模型结构的模型压缩算法库
Stars: ✭ 126 (+133.33%)
Mutual labels:  onnx
epic-awesome-gamer
🍷 Gracefully claim weekly free games and monthly content from Epic Store.
Stars: ✭ 600 (+1011.11%)
Mutual labels:  onnx
ONNX.jl
Read ONNX graphs in Julia
Stars: ✭ 112 (+107.41%)
Mutual labels:  onnx
onnx2caffe
pytorch to caffe by onnx
Stars: ✭ 341 (+531.48%)
Mutual labels:  onnx
TPU-MobilenetSSD
Edge TPU Accelerator / Multi-TPU + MobileNet-SSD v2 + Python + Async + LattePandaAlpha/RaspberryPi3/LaptopPC
Stars: ✭ 82 (+51.85%)
Mutual labels:  colaboratory
onnx learn
No description or website provided.
Stars: ✭ 74 (+37.04%)
Mutual labels:  onnx
arcface retinaface mxnet2onnx
arcface and retinaface model convert mxnet to onnx.
Stars: ✭ 53 (-1.85%)
Mutual labels:  onnx
mediapipe plus
The purpose of this project is to apply mediapipe to more AI chips.
Stars: ✭ 38 (-29.63%)
Mutual labels:  onnx
AgentOCR
一个多语言支持、易使用的 OCR 项目。An easy-to-use OCR project with multilingual support.
Stars: ✭ 98 (+81.48%)
Mutual labels:  onnx
ai-serving
Serving AI/ML models in the open standard formats PMML and ONNX with both HTTP (REST API) and gRPC endpoints
Stars: ✭ 122 (+125.93%)
Mutual labels:  onnx
emnist dl2prod
JuPyter Notebooks and Python Package for Deep Learning Model Exploration, Translation and Deployment
Stars: ✭ 31 (-42.59%)
Mutual labels:  onnx
Peppa-Facial-Landmark-PyTorch
Facial Landmark Detection based on PyTorch
Stars: ✭ 172 (+218.52%)
Mutual labels:  onnx
pytorch-android
[EXPERIMENTAL] Demo of using PyTorch 1.0 inside an Android app. Test with your own deep neural network such as ResNet18/SqueezeNet/MobileNet v2 and a phone camera.
Stars: ✭ 105 (+94.44%)
Mutual labels:  onnx
InsightFace-REST
InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.
Stars: ✭ 308 (+470.37%)
Mutual labels:  onnx
PSGAN-NCNN
PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡
Stars: ✭ 140 (+159.26%)
Mutual labels:  onnx

AnimeGANv2-ONNX-Sample

 
PyTorch Implementation of AnimeGANv2のPythonでのONNX推論サンプルです。
ONNXに変換したモデルも同梱しています。
変換自体を試したい方はColaboratoryなどでAnimeGANv2_Convert2ONNX.ipynbを使用ください。

Requirement(ONNX変換)

  • Pytorch 1.9.0 or later
  • onnx 1.10.2 or later
  • onnx-simplifier 0.3.6 or later

Requirement(ONNX推論)

  • OpenCV 4.5.3.56 or later
  • onnxruntime-gpu 1.9.0 or later
    ※onnxruntimeでも動作しますが、推論時間がかかるのでGPUをお勧めします

推論速度参考値

GeForce GTX 1050 Ti:約290ms
GeForce RTX 3060:約120ms

Demo

デモの実行方法は以下です。

python sample_onnx.py
  • --device
    カメラデバイス番号の指定
    デフォルト:0
  • --movie
    動画ファイルの指定 ※指定時はカメラデバイスより優先
    デフォルト:指定なし
  • --width
    カメラキャプチャ時の横幅
    デフォルト:960
  • --height
    カメラキャプチャ時の縦幅
    デフォルト:540
  • --model
    ロードするモデルの格納パス
    デフォルト:model/face_paint_512_v2_0.onnx
  • --input_shape
    モデルの入力サイズ
    デフォルト:512

Application example

応用例です。

Reference

Author

高橋かずひと(https://twitter.com/KzhtTkhs)

License

AnimeGANv2-ONNX-Sample is under MIT License.

License(Image)

女性の画像はフリー素材ぱくたそ様の写真を利用しています。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].