RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation

Overview

RIFE

RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation

Ported from https://github.com/hzwer/arXiv2020-RIFE

Dependencies

  • NumPy
  • PyTorch, preferably with CUDA. Note that torchvision and torchaudio are not required and hence can be omitted from the command.
  • VapourSynth

Installation

pip install --upgrade vsrife

Usage

from vsrife import RIFE

ret = RIFE(clip)

See __init__.py for the description of the parameters.

Comments
  • Getting Error when interpolating

    Getting Error when interpolating

        model.load_model(os.path.join(os.path.dirname(__file__), model_dir), -1)
      File "C:\Users\\AppData\Local\Programs\Python\Python39\lib\site-packages\vsrife\RIFE_HDv2.py", line 164, in load_model
        convert(torch.load('{}/flownet.pkl'.format(path), map_location=self.torch_device)))
      File "C:\Users\\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\serialization.py", line 608, in load
        return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
      File "C:\Users\\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\serialization.py", line 777, in _legacy_load
        magic_number = pickle_module.load(f, **pickle_load_args)
    EOFError: Ran out of input  ```
    
    Source file is a 720p 30fps mp4, loaded into VS through Lsmash source, set the format to RGBS. Nothing else
    System specs are R7 3700x, 32GB of ram and a RTX 3060
    
    
    opened by banjaminicc 4
  • Small feature request for RIFEv4: target fps as alternative to multiplier

    Small feature request for RIFEv4: target fps as alternative to multiplier

    I would it be possible to allow setting a target fps instead of a multiplier when using RIFEv4? When going from for example 23.976 (24000/1001) to 60 fps, having to use (60 * 1001 / 24000 =) 2,5025 is kind of annoying. ;) I know could write a wrapper arount the rife.RIFE but I suspect depending on the resulting float it would be more accurate if this was done inside the filter.

    opened by Selur 3
  • vs-rife + latest vs-dpir don't work

    vs-rife + latest vs-dpir don't work

    When using just vs-rife:

    # Imports
    import vapoursynth as vs
    # getting Vapoursynth core
    core = vs.core
    # Loading Plugins
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/MiscFilter/MiscFilters/MiscFilters.dll")
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/DeinterlaceFilter/TIVTC/libtivtc.dll")
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/SourceFilter/d2vSource/d2vsource.dll")
    # source: 'C:\Users\Selur\Desktop\VTS_01_1.VOB'
    # current color space: YUV420P8, bit depth: 8, resolution: 720x480, fps: 29.97, color matrix: 470bg, yuv luminance scale: limited, scanorder: telecine
    # Loading C:\Users\Selur\Desktop\VTS_01_1.VOB using D2VSource
    clip = core.d2v.Source(input="E:/Temp/vob_941fdaaeda22090766694391cc4281d5_853323747.d2v")
    # Setting color matrix to 470bg.
    clip = core.std.SetFrameProps(clip, _Matrix=5)
    clip = clip if not core.text.FrameProps(clip,'_Transfer') else core.std.SetFrameProps(clip, _Transfer=5)
    clip = clip if not core.text.FrameProps(clip,'_Primaries') else core.std.SetFrameProps(clip, _Primaries=5)
    # Setting color range to TV (limited) range.
    clip = core.std.SetFrameProp(clip=clip, prop="_ColorRange", intval=1)
    # making sure frame rate is set to 29.970
    clip = core.std.AssumeFPS(clip=clip, fpsnum=30000, fpsden=1001)
    # Deinterlacing using TIVTC
    clip = core.tivtc.TFM(clip=clip)
    clip = core.tivtc.TDecimate(clip=clip, mode=7, rate=10, dupThresh=0.04, vidThresh=3.50, sceneThresh=15.00)# new fps: 10
    # make sure content is preceived as frame based
    clip = core.std.SetFieldBased(clip, 0)
    clip = core.misc.SCDetect(clip=clip,threshold=0.150)
    from vsrife import RIFE
    # adjusting color space from YUV420P8 to RGBS for VsTorchRIFE
    clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s="470bg", range_s="limited")
    # adjusting frame count&rate with RIFE (torch)
    clip = RIFE(clip, multi=3, device_type='cuda', device_index=0) # new fps: 20
    # adjusting output color from: RGBS to YUV420P8 for x264Model
    clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P8, matrix_s="470bg", range_s="limited")
    # set output frame rate to 30.000fps
    clip = core.std.AssumeFPS(clip=clip, fpsnum=30, fpsden=1)
    # Output
    clip.set_output()
    

    everything works. But when I add latest vs-dpir:

    # Imports
    import vapoursynth as vs
    # getting Vapoursynth core
    core = vs.core
    import os
    import site
    # Import libraries for onnxruntime
    from ctypes import WinDLL
    path = site.getsitepackages()[0]+'/onnxruntime_dlls/'
    WinDLL(path+'cublas64_11.dll')
    WinDLL(path+'cudart64_110.dll')
    WinDLL(path+'cudnn64_8.dll')
    WinDLL(path+'cudnn_cnn_infer64_8.dll')
    WinDLL(path+'cudnn_ops_infer64_8.dll')
    WinDLL(path+'cufft64_10.dll')
    WinDLL(path+'cufftw64_10.dll')
    WinDLL(path+'nvinfer.dll')
    WinDLL(path+'nvinfer_plugin.dll')
    WinDLL(path+'nvparsers.dll')
    WinDLL(path+'nvonnxparser.dll')
    # Loading Plugins
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/MiscFilter/MiscFilters/MiscFilters.dll")
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/DeinterlaceFilter/TIVTC/libtivtc.dll")
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/SourceFilter/d2vSource/d2vsource.dll")
    # source: 'C:\Users\Selur\Desktop\VTS_01_1.VOB'
    # current color space: YUV420P8, bit depth: 8, resolution: 720x480, fps: 29.97, color matrix: 470bg, yuv luminance scale: limited, scanorder: telecine
    # Loading C:\Users\Selur\Desktop\VTS_01_1.VOB using D2VSource
    clip = core.d2v.Source(input="E:/Temp/vob_941fdaaeda22090766694391cc4281d5_853323747.d2v")
    # Setting color matrix to 470bg.
    clip = core.std.SetFrameProps(clip, _Matrix=5)
    clip = clip if not core.text.FrameProps(clip,'_Transfer') else core.std.SetFrameProps(clip, _Transfer=5)
    clip = clip if not core.text.FrameProps(clip,'_Primaries') else core.std.SetFrameProps(clip, _Primaries=5)
    # Setting color range to TV (limited) range.
    clip = core.std.SetFrameProp(clip=clip, prop="_ColorRange", intval=1)
    # making sure frame rate is set to 29.970
    clip = core.std.AssumeFPS(clip=clip, fpsnum=30000, fpsden=1001)
    # Deinterlacing using TIVTC
    clip = core.tivtc.TFM(clip=clip)
    clip = core.tivtc.TDecimate(clip=clip, mode=7, rate=10, dupThresh=0.04, vidThresh=3.50, sceneThresh=15.00)# new fps: 10
    # make sure content is preceived as frame based
    clip = core.std.SetFieldBased(clip, 0)
    from vsdpir import DPIR
    # adjusting color space from YUV420P8 to RGBS for vsDPIRDenoise
    clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s="470bg", range_s="limited")
    # denoising using DPIRDenoise
    clip = DPIR(clip=clip, strength=15.000, task="denoise", provider=1, device_id=0)
    clip = core.resize.Bicubic(clip=clip, format=vs.YUV444P16, matrix_s="470bg", range_s="limited")
    clip = core.misc.SCDetect(clip=clip,threshold=0.150)
    from vsrife import RIFE
    # adjusting color space from YUV444P16 to RGBS for VsTorchRIFE
    clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s="470bg", range_s="limited")
    # adjusting frame count&rate with RIFE (torch)
    clip = RIFE(clip, multi=3, device_type='cuda', device_index=0) # new fps: 20
    # adjusting output color from: RGBS to YUV420P8 for x264Model
    clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P8, matrix_s="470bg", range_s="limited")
    # set output frame rate to 30.000fps
    clip = core.std.AssumeFPS(clip=clip, fpsnum=30, fpsden=1)
    # Output
    clip.set_output()
    

    I get:

    Python exception: [WinError 127] Die angegebene Prozedur wurde nicht gefunden. Error loading "I:\Hybrid\64bit\Vapoursynth\Lib/site-packages\torch\lib\cudnn_cnn_train64_8.dll" or one of its dependencies.
    

    Using just vs-dpir:

    # Imports
    import vapoursynth as vs
    # getting Vapoursynth core
    core = vs.core
    import os
    import site
    # Import libraries for onnxruntime
    from ctypes import WinDLL
    path = site.getsitepackages()[0]+'/onnxruntime_dlls/'
    WinDLL(path+'cublas64_11.dll')
    WinDLL(path+'cudart64_110.dll')
    WinDLL(path+'cudnn64_8.dll')
    WinDLL(path+'cudnn_cnn_infer64_8.dll')
    WinDLL(path+'cudnn_ops_infer64_8.dll')
    WinDLL(path+'cufft64_10.dll')
    WinDLL(path+'cufftw64_10.dll')
    WinDLL(path+'nvinfer.dll')
    WinDLL(path+'nvinfer_plugin.dll')
    WinDLL(path+'nvparsers.dll')
    WinDLL(path+'nvonnxparser.dll')
    # Loading Plugins
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/DeinterlaceFilter/TIVTC/libtivtc.dll")
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/SourceFilter/d2vSource/d2vsource.dll")
    # source: 'C:\Users\Selur\Desktop\VTS_01_1.VOB'
    # current color space: YUV420P8, bit depth: 8, resolution: 720x480, fps: 29.97, color matrix: 470bg, yuv luminance scale: limited, scanorder: telecine
    # Loading C:\Users\Selur\Desktop\VTS_01_1.VOB using D2VSource
    clip = core.d2v.Source(input="E:/Temp/vob_941fdaaeda22090766694391cc4281d5_853323747.d2v")
    # Setting color matrix to 470bg.
    clip = core.std.SetFrameProps(clip, _Matrix=5)
    clip = clip if not core.text.FrameProps(clip,'_Transfer') else core.std.SetFrameProps(clip, _Transfer=5)
    clip = clip if not core.text.FrameProps(clip,'_Primaries') else core.std.SetFrameProps(clip, _Primaries=5)
    # Setting color range to TV (limited) range.
    clip = core.std.SetFrameProp(clip=clip, prop="_ColorRange", intval=1)
    # making sure frame rate is set to 29.970
    clip = core.std.AssumeFPS(clip=clip, fpsnum=30000, fpsden=1001)
    # Deinterlacing using TIVTC
    clip = core.tivtc.TFM(clip=clip)
    clip = core.tivtc.TDecimate(clip=clip, mode=7, rate=10, dupThresh=0.04, vidThresh=3.50, sceneThresh=15.00)# new fps: 10
    # make sure content is preceived as frame based
    clip = core.std.SetFieldBased(clip, 0)
    from vsdpir import DPIR
    # adjusting color space from YUV420P8 to RGBS for vsDPIRDenoise
    clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s="470bg", range_s="limited")
    # denoising using DPIRDenoise
    clip = DPIR(clip=clip, strength=15.000, task="denoise", provider=1, device_id=0)
    # adjusting output color from: RGBS to YUV420P8 for x264Model
    clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P8, matrix_s="470bg", range_s="limited")
    # set output frame rate to 10.000fps
    clip = core.std.AssumeFPS(clip=clip, fpsnum=10, fpsden=1)
    # Output
    clip.set_output()
    

    works fine.

    -> do you have an idea how I could fix this?

    opened by Selur 3
  • half the image is broken when using 4k content

    half the image is broken when using 4k content

    I get a broken output (see attachment), when using:

    # Imports
    import vapoursynth as vs
    # getting Vapoursynth core
    core = vs.core
    # Loading Plugins
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/MiscFilter/MiscFilters/MiscFilters.dll")
    core.std.LoadPlugin(path="i:/Hybrid/64bit/vsfilters/SourceFilter/LSmashSource/vslsmashsource.dll")
    # source: 'G:\TestClips&Co\files\MPEG-4 H.264\4k\Back to the Future (1985) 4k 10bit - 0.10.35-0.11.35.mkv'
    # current color space: YUV420P10, bit depth: 10, resolution: 3840x2076, fps: 23.976, color matrix: 2020ncl, yuv luminance scale: limited, scanorder: progressive
    # Loading G:\TestClips&Co\files\MPEG-4 H.264\4k\Back to the Future (1985) 4k 10bit - 0.10.35-0.11.35.mkv using LWLibavSource
    clip = core.lsmas.LWLibavSource(source="G:/TestClips&Co/files/MPEG-4 H.264/4k/Back to the Future (1985) 4k 10bit - 0.10.35-0.11.35.mkv", format="YUV420P10", cache=0, fpsnum=24000, fpsden=1001, prefer_hw=1)
    # Setting color matrix to 2020ncl.
    clip = core.std.SetFrameProps(clip, _Matrix=9)
    clip = clip if not core.text.FrameProps(clip,'_Transfer') else core.std.SetFrameProps(clip, _Transfer=9)
    clip = clip if not core.text.FrameProps(clip,'_Primaries') else core.std.SetFrameProps(clip, _Primaries=9)
    # Setting color range to TV (limited) range.
    clip = core.std.SetFrameProp(clip=clip, prop="_ColorRange", intval=1)
    # making sure frame rate is set to 23.976
    clip = core.std.AssumeFPS(clip=clip, fpsnum=24000, fpsden=1001)
    clip = core.misc.SCDetect(clip=clip,threshold=0.150)
    from vsrife import RIFE
    # adjusting color space from YUV420P10 to RGBS for VsTorchRIFE
    clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s="2020ncl", range_s="limited")
    # adjusting frame count&rate with RIFE (torch)
    clip = RIFE(clip, scale=0.5, multi=3, device_type='cuda', device_index=0, fp16=True) # new fps: 71.928
    # adjusting output color from: RGBS to YUV420P8 for x264Model
    clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P8, matrix_s="2020ncl", range_s="limited", dither_type="error_diffusion")
    # set output frame rate to 71.928fps
    clip = core.std.AssumeFPS(clip=clip, fpsnum=8991, fpsden=125)
    # Output
    clip.set_output()
    

    tried different scale values, fp16 disabled, without scene change detection and other values for mult, nothing helped. https://github.com/HomeOfVapourSynthEvolution/VapourSynth-RIFE-ncnn-Vulkan works fine. 2k content also works fine. I tried different source filters and different files. Would be nice if this could be fixed.

    attachment was too large: https://ibb.co/WGT9pvL

    opened by Selur 2
  • Vapoursynth R58 and Python 3.10 compatibilty

    Vapoursynth R58 and Python 3.10 compatibilty

    trying to install vs-rife in Vapoursynth R58 I get:

    I:\Hybrid\64bit\Vapoursynth>python -m pip install --upgrade vsrife
    Collecting vsrife
      Using cached vsrife-2.0.0-py3-none-any.whl (32.5 MB)
    Requirement already satisfied: torch>=1.9.0 in i:\hybrid\64bit\vapoursynth\lib\site-packages (from vsrife) (1.11.0+cu113)
    Requirement already satisfied: numpy in i:\hybrid\64bit\vapoursynth\lib\site-packages (from vsrife) (1.22.3)
    Collecting VapourSynth>=55
      Using cached VapourSynth-57.zip (567 kB)
      Preparing metadata (setup.py) ... error
      error: subprocess-exited-with-error
    
      × python setup.py egg_info did not run successfully.
      │ exit code: 1
      ╰─> [15 lines of output]
          Traceback (most recent call last):
            File "C:\Users\Selur\AppData\Local\Temp\pip-install-s7976394\vapoursynth_701a37362cd045f58da4818d07217c99\setup.py", line 64, in <module>
              dll_path = query(winreg.HKEY_LOCAL_MACHINE, REGISTRY_PATH, REGISTRY_KEY)
            File "C:\Users\Selur\AppData\Local\Temp\pip-install-s7976394\vapoursynth_701a37362cd045f58da4818d07217c99\setup.py", line 38, in query
              reg_key = winreg.OpenKey(hkey, path, 0, winreg.KEY_READ)
          FileNotFoundError: [WinError 2] Das System kann die angegebene Datei nicht finden
    
          During handling of the above exception, another exception occurred:
    
          Traceback (most recent call last):
            File "<string>", line 2, in <module>
            File "<pip-setuptools-caller>", line 34, in <module>
            File "C:\Users\Selur\AppData\Local\Temp\pip-install-s7976394\vapoursynth_701a37362cd045f58da4818d07217c99\setup.py", line 67, in <module>
              raise OSError("Couldn't detect vapoursynth installation path")
          OSError: Couldn't detect vapoursynth installation path
          [end of output]
    
      note: This error originates from a subprocess, and is likely not a problem with pip.
    error: metadata-generation-failed
    
    × Encountered error while generating package metadata.
    ╰─> See above for output.
    
    note: This is an issue with the package mentioned above, not pip.
    hint: See above for details.
    

    any idea how to fix it?

    opened by Selur 2
  • How to set 'clip.num_frames

    How to set 'clip.num_frames

    How to set the frames numbers?I only found the "multi: int ="in "init.py".Can I set the whole number of the frames numbers?Like 60 fps?Thanks!

    opened by feaonal 2
  • Requesting example vapoursynth script

    Requesting example vapoursynth script

    I tried to create a valid script for a while, but I can't make it run.

    from vsrife import RIFE
    import vapoursynth as vs
    core = vs.core
    core.std.LoadPlugin(path='/usr/lib/x86_64-linux-gnu/libffms2.so')
    clip = core.ffms2.Source(source='test.webm')
    print(clip) # YUV420P8
    clip = vs.core.resize.Bicubic(clip, format=vs.RGBS)
    print(clip) # RGBS
    clip = RIFE(clip)
    clip.set_output()
    
    vspipe --y4m inference.py - | x264 - --demuxer y4m -o example.mkv
    
    Error: Failed to retrieve frame 0 with error: Resize error: Resize error 3074: no path between colorspaces (2/2/2 => 0/2/2). May need to specify additional colorspace parameters.
    

    Can I get an example that should actually work?

    opened by styler00dollar 2
  • [Q] 0bit models in the repo

    [Q] 0bit models in the repo

    Hi

    i see in the model folders, have a files (models?) with 0bits, i presume when the plugin "learn", the models is filled with the data

    this is correct?

    then, in a system with install this plugin as system-wide, these models should be have a write permissions? (in case of linux)

    greetings

    opened by sl1pkn07 2
  • Wrong output framerate

    Wrong output framerate

    That - https://github.com/HolyWu/vs-rife/blob/91e894f41cbdfb458ef8f776c47c7f652158bc6f/vsrife/init.py#L280 - doesn't work as expected because of two reasons:

    1. clip.fps.numerator / denominator can be 0 / 1 (from the docs: "It is 0/1 when the clip has a variable framerate")
    2. there's a frame duration attached to each frame, and it seems like FrameEval(frame_adjuster) return frames with the original durations, not the ones from format_clip

    A quick fix that works:

        clip0 = vs.core.std.Interleave([clip] * factor_num)
        if factor_den>1:
            clip0 = clip0.std.SelectEvery(cycle=factor_den,offsets=0)
        clip1 = clip.std.DuplicateFrames(frames=clip.num_frames - 1).std.DeleteFrames(frames=0)
        clip1 = vs.core.std.Interleave([clip1] * factor_num)
        if factor_den>1:
            clip1 = clip1.std.SelectEvery(cycle=factor_den,offsets=0)
    
    opened by chainikdn 1
  • How to set clip.num_frames

    How to set clip.num_frames

    How to set the frames numbers?I only found the "multi: int ="in "init.py".Can I set the whole number of the frames numbers?Like 60 fps?Thanks!

    opened by feaonal 0
Releases(v3.1.0)
A PyTorch Toolbox for Face Recognition

FaceX-Zoo FaceX-Zoo is a PyTorch toolbox for face recognition. It provides a training module with various supervisory heads and backbones towards stat

JDAI-CV 1.6k Jan 06, 2023
Pytorch implementation of Integrating Tree Path in Transformer for Code Representation

This is an official Pytorch implementation of the approaches proposed in: Han Peng, Ge Li, Wenhan Wang, Yunfei Zhao, Zhi Jin “Integrating Tree Path in

Han Peng 16 Dec 23, 2022
A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

ARES This repository contains the code for ARES (Adversarial Robustness Evaluation for Safety), a Python library for adversarial machine learning rese

Tsinghua Machine Learning Group 377 Dec 20, 2022
(CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

ClassSR (CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic Paper Authors: Xiangtao Kong, Hengyuan

Xiangtao Kong 308 Jan 05, 2023
Detect roadway lanes using Python OpenCV for project during the 5th semester at DHBW Stuttgart for lecture in digital image processing.

Find Line Detection (Image Processing) Identifying lanes of the road is very common task that human driver performs. It's important to keep the vehicl

LMF 4 Jun 21, 2022
FrankMocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

FrankMocap pursues an easy-to-use single view 3D motion capture system developed by Facebook AI Research (FAIR). FrankMocap provides state-of-the-art 3D pose estimation outputs for body, hand, and bo

Facebook Research 1.9k Jan 07, 2023
A PyTorch Reimplementation of TecoGAN: Temporally Coherent GAN for Video Super-Resolution

TecoGAN-PyTorch Introduction This is a PyTorch reimplementation of TecoGAN: Temporally Coherent GAN for Video Super-Resolution (VSR). Please refer to

165 Dec 17, 2022
Accurate Phylogenetic Inference with Symmetry-Preserving Neural Networks

Accurate Phylogenetic Inference with a Symmetry-preserving Neural Network Model Claudia Solis-Lemus Shengwen Yang Leonardo Zepeda-Núñez This repositor

Leonardo Zepeda-Núñez 2 Feb 11, 2022
Cossim - Sharpened Cosine Distance implementation in PyTorch

Sharpened Cosine Distance PyTorch implementation of the Sharpened Cosine Distanc

Istvan Fehervari 10 Mar 22, 2022
基于Flask开发后端、VUE开发前端框架,在WEB端部署YOLOv5目标检测模型

基于Flask开发后端、VUE开发前端框架,在WEB端部署YOLOv5目标检测模型

37 Jan 01, 2023
BLEURT is a metric for Natural Language Generation based on transfer learning.

BLEURT: a Transfer Learning-Based Metric for Natural Language Generation BLEURT is an evaluation metric for Natural Language Generation. It takes a pa

Google Research 492 Jan 05, 2023
Learnable Motion Coherence for Correspondence Pruning

Learnable Motion Coherence for Correspondence Pruning Yuan Liu, Lingjie Liu, Cheng Lin, Zhen Dong, Wenping Wang Project Page Any questions or discussi

liuyuan 41 Nov 30, 2022
This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

AlphaRotate: A Rotation Detection Benchmark using TensorFlow Abstract AlphaRotate is maintained by Xue Yang with Shanghai Jiao Tong University supervi

yangxue 972 Jan 05, 2023
A library for low-memory inferencing in PyTorch.

Pylomin Pylomin (PYtorch LOw-Memory INference) is a library for low-memory inferencing in PyTorch. Installation ... Usage For example, the following c

3 Oct 26, 2022
Trajectory Variational Autoencder baseline for Multi-Agent Behavior challenge 2022

MABe_2022_TVAE: a Trajectory Variational Autoencoder baseline for the 2022 Multi-Agent Behavior challenge This repository contains jupyter notebooks t

Andrew Ulmer 15 Nov 08, 2022
Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments

Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments Paper: arXiv (ICRA 2021) Video : https://youtu.be/CC

Sachini Herath 68 Jan 03, 2023
Constructing interpretable quadratic accuracy predictors to serve as an objective function for an IQCQP problem that represents NAS under latency constraints and solve it with efficient algorithms.

IQNAS: Interpretable Integer Quadratic programming Neural Architecture Search Realistic use of neural networks often requires adhering to multiple con

0 Oct 24, 2021
The software associated with a paper accepted at EMNLP 2021 titled "Open Knowledge Graphs Canonicalization using Variational Autoencoders".

Open-KG-canonicalization The software associated with a paper accepted at EMNLP 2021 titled "Open Knowledge Graphs Canonicalization using Variational

International Business Machines 13 Nov 11, 2022
Urban mobility simulations with Python3, RLlib (Deep Reinforcement Learning) and Mesa (Agent-based modeling)

Deep Reinforcement Learning for Smart Cities Documentation RLlib: https://docs.ray.io/en/master/rllib.html Mesa: https://mesa.readthedocs.io/en/stable

1 May 15, 2022
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Apache MXNet (incubating) for Deep Learning Master Docs License Apache MXNet (incubating) is a deep learning framework designed for both efficiency an

ROCm Software Platform 29 Nov 16, 2022