Resources

Datasets

  1. Google Audio Set: https://research.google.com/audioset/index.html
  2. Google Landmark Recognition Dataset: https://github.com/cvdfoundation/google-landmark
  3. YouTube Videos: https://research.google/tools/datasets/youtube-8m/
  4. Music Generation: https://magenta.tensorflow.org/datasets
  5. word2vec: https://code.google.com/archive/p/word2vec/
  6. ImageNet: https://www.image-net.org/
  7. Google Know Your Data: https://knowyourdata-tfds.withgoogle.com/
  8. Cityscapes: https://www.cityscapes-dataset.com/
  9. Scene Segmentation: https://groups.csail.mit.edu/vision/datasets/ADE20K/
  10. Coco: https://cocodataset.org/#home
  11. CIFAR-100: https://keras.io/api/datasets/cifar100/
  12. Pascal: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/segexamples/index.html

Cloud APIs

  1. Google Landmark Detection: https://cloud.google.com/vision/docs/detecting-landmarks
  2. AWS Transcribe (Audio to Text): https://aws.amazon.com/transcribe/
  3. AWS Polly (Text 2 Speech): https://aws.amazon.com/polly/
  4. Alexa Skills: https://developer.amazon.com/en-US/alexa/alexa-skills-kit
  5. AWS API Gateway: https://aws.amazon.com/api-gateway/
  6. AWS Translate: https://aws.amazon.com/translate/
  7. AWS Textract: https://aws.amazon.com/textract/
  8. AWS Text Analytics: https://aws.amazon.com/comprehend/
  9. AWS Sagemaker: https://aws.amazon.com/sagemaker/

Pre-Trained Models

  1. Mobile-Net: https://github.com/tensorflow/tfjs-models/tree/master/mobilenet
  2. Coco-SSD: https://github.com/tensorflow/tfjs-models/tree/master/coco-ssd
  3. Person Segmentation: https://github.com/tensorflow/tfjs-models/tree/master/body-pix
  4. Pose Capture: https://github.com/tensorflow/tfjs-models/tree/master/pose-detection
  5. Gesture: https://github.com/tensorflow/tfjs-models/tree/master/handpose
  6. Facial Landmarks: https://github.com/tensorflow/tfjs-models/tree/master/face-landmarks-detection

Tools & Libraries

  1. Google Colab: https://colab.research.google.com/
  2. Teachable Machines: https://teachablemachine.withgoogle.com/
  3. Transfer Learning: https://github.com/tensorflow/tfjs-models/tree/master/knn-classifier
  4. PyAudio: http://people.csail.mit.edu/hubert/pyaudio/
  5. DeOldify: https://github.com/jantic/DeOldify
  6. Keras: https://keras.io/api/applications/
  7. PyTorch: https://pytorch.org/tutorials/

Music & Audio

  1. AWS Deep Composer: https://aws.amazon.com/deepcomposer/
  2. Google Magenta: https://magenta.tensorflow.org/
  3. Open AI Jukebox: https://openai.com/blog/jukebox/
  4. Tone.JS MIDI Parser: https://tonejs.github.io/Midi/
  5. Tone.JS: https://tonejs.github.io/
  6. Teachable Machines Audio Classifier: https://teachablemachine.withgoogle.com/train/audio
  7. Google Audio Dataset: https://research.google.com/audioset/index.html

Augmented / Mixed Reality

  1. Spark AR: https://sparkar.facebook.com/ar-studio/
  2. Lens Studio: https://lensstudio.snapchat.com/
  3. AR Core: https://developers.google.com/ar
  4. Aframe.io: https://aframe.io/

3D Models

  1. Sketchfab: https://sketchfab.com
  2. Blender: https://www.blender.org/
  3. Three.js: https://threejs.org/
  4. Polligon Textures & Materials: https://www.poliigon.com/
  5. Adobe Substance: https://www.substance3d.com/
  6. Polligon (free): https://www.poliigon.com/textures/free