ailia-models

ailia-models copied to clipboard

ADD yolo3d

1

https://github.com/maudzung/YOLO3D-YOLOv4-PyTorch

kyakuno

ADD FairMOT

1

https://github.com/ifzhang/FairMOT

kyakuno

https://github.com/ucbdrive/3d-vehicle-tracking BSD

kyakuno

set memory_mode option for models that require 4GiB or more memory

1

- [x] face_detection/retinaface - [x] image_segmentation/dense_prediction_transformers - [x] image_segmentation/pytorch-unet - [x] object_tracking/bytetrack - [x] super_resolution/han - [x] super_resolution/real-esrgan - [x] text_detection/craft_pytorch - [x] low_light_image_enhancement/agllnet

kzmogi

現状はU_FP32を使用しているが、リファレンスコードを見るとS_FP32が正しいように思われる。 https://github.com/qfgaohao/pytorch-ssd/blob/master/vision/ssd/config/mobilenetv1_ssd_config.py

kyakuno

https://github.com/axinc-ai/ailia-models/issues/677

ooe1123

https://github.com/weichen582/GLADNet

kyakuno

https://github.com/rhgao/co-separation CC

kyakuno

Implement Piano transcription

1

https://github.com/axinc-ai/ailia-models/issues/710

ooe1123

ADD yukarin

6

https://github.com/Hiroshiba/realtime-yukarin mit voice conversion

kyakuno