dmlc/decord

pip install decord

# official PPA comes with ffmpeg 2.8, which lacks tons of features, we use ffmpeg 4.0 here
sudo add-apt-repository ppa:jonathonf/ffmpeg-4 # for ubuntu20.04 official PPA is already version 4.2, you may skip this step
sudo apt-get update
sudo apt-get install -y build-essential python3-dev python3-setuptools make cmake
sudo apt-get install -y ffmpeg libavcodec-dev libavfilter-dev libavformat-dev libavutil-dev
# note: make sure you have cmake 3.8 or later, you can install from cmake official website if it's too old

git clone --recursive https://github.com/dmlc/decord

cd decord
mkdir build && cd build
cmake .. -DUSE_CUDA=0 -DCMAKE_BUILD_TYPE=Release
make

cmake .. -DUSE_CUDA=ON -DCMAKE_BUILD_TYPE=Release

cd ../python
# option 1: add python path to $PYTHONPATH, you will need to install numpy separately
pwd=$PWD
echo "PYTHONPATH=$PYTHONPATH:$pwd" >> ~/.bashrc
source ~/.bashrc
# option 2: install with setuptools
python3 setup.py install --user

xcode-select --install

brew install cmake ffmpeg
# note: make sure you have cmake 3.8 or later, you can install from cmake official website if it's too old

git clone --recursive https://github.com/dmlc/decord

cd decord
mkdir build && cd build
cmake .. -DCMAKE_BUILD_TYPE=Release
make

cd ../python
# option 1: add python path to $PYTHONPATH, you will need to install numpy separately
pwd=$PWD
echo "PYTHONPATH=$PYTHONPATH:$pwd" >> ~/.bash_profile
source ~/.bash_profile
# option 2: install with setuptools
python3 setup.py install --user

cd your-workspace
git clone --recursive https://github.com/dmlc/decord
cd decord
mkdir build
cd build
cmake -DCMAKE_CXX_FLAGS="/DDECORD_EXPORTS" -DCMAKE_CONFIGURATION_TYPES="Release" -G "Visual Studio 15 2017 Win64" ..
# open `decord.sln` and build project

from decord import VideoReader
from decord import cpu, gpu

vr = VideoReader('examples/flipping_a_pancake.mkv', ctx=cpu(0))
# a file like object works as well, for in-memory decoding
with open('examples/flipping_a_pancake.mkv', 'rb') as f:
  vr = VideoReader(f, ctx=cpu(0))
print('video frames:', len(vr))
# 1. the simplest way is to directly access frames
for i in range(len(vr)):
    # the video reader will handle seeking and skipping in the most efficient manner
    frame = vr[i]
    print(frame.shape)

# To get multiple frames at once, use get_batch
# this is the efficient way to obtain a long list of frames
frames = vr.get_batch([1, 3, 5, 7, 9])
print(frames.shape)
# (5, 240, 320, 3)
# duplicate frame indices will be accepted and handled internally to avoid duplicate decoding
frames2 = vr.get_batch([1, 2, 3, 2, 3, 4, 3, 4, 5]).asnumpy()
print(frames2.shape)
# (9, 240, 320, 3)

# 2. you can do cv2 style reading as well
# skip 100 frames
vr.skip_frames(100)
# seek to start
vr.seek(0)
batch = vr.next()
print('frame shape:', batch.shape)
print('numpy frames:', batch.asnumpy())

from decord import VideoLoader
from decord import cpu, gpu

vl = VideoLoader(['1.mp4', '2.avi', '3.mpeg'], ctx=[cpu(0)], shape=(2, 320, 240, 3), interval=1, skip=5, shuffle=1)
print('Total batches:', len(vl))

for batch in vl:
    print(batch[0].shape)

shuffle = -1  # smart shuffle mode, based on video properties, (not implemented yet)
shuffle = 0  # all sequential, no seeking, following initial filename order
shuffle = 1  # random filename order, no random access for each video, very efficient
shuffle = 2  # random order
shuffle = 3  # random frame access in each video only

from decord import AudioReader
from decord import cpu, gpu

# You can specify the desired sample rate and channel layout
# For channels there are two options: default to the original layout or mono
ar = AudioReader('example.mp3', ctx=cpu(0), sample_rate=44100, mono=False)
print('Shape of audio samples: ', ar.shape())
# To access the audio samples
print('The first sample: ', ar[0])
print('The first five samples: ', ar[0:5])
print('Get a batch of samples: ', ar.get_batch([1,3,5]))

from decord import AVReader
from decord import cpu, gpu

av = AVReader('example.mov', ctx=cpu(0))
# To access both the video frames and corresponding audio samples
audio, video = av[0:20]
# Each element in audio will be a batch of samples corresponding to a frame of video
print('Frame #: ', len(audio))
print('Shape of the audio samples of the first frame: ', audio[0].shape)
print('Shape of the first frame: ', video.asnumpy()[0].shape)
# Similarly, to get a batch
audio2, video2 = av.get_batch([1,3,5])

import decord
vr = decord.VideoReader('examples/flipping_a_pancake.mkv')
print('native output:', type(vr[0]), vr[0].shape)
# native output: <class 'decord.ndarray.NDArray'>, (240, 426, 3)
# you only need to set the output type once
decord.bridge.set_bridge('mxnet')
print(type(vr[0], vr[0].shape))
# <class 'mxnet.ndarray.ndarray.NDArray'> (240, 426, 3)
# or pytorch and tensorflow(>=2.2.0)
decord.bridge.set_bridge('torch')
decord.bridge.set_bridge('tensorflow')
# or back to decord native format
decord.bridge.set_bridge('native')