Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tugstugi/dl-colab-notebooks
Try out deep learning models online on Google Colab
https://github.com/tugstugi/dl-colab-notebooks
cnn colab-notebook deep-learning deep-neural-networks google-colab google-colaboratory jupyter-notebook jupyter-notebooks pytorch tensorflow
Last synced: 3 days ago
JSON representation
Try out deep learning models online on Google Colab
- Host: GitHub
- URL: https://github.com/tugstugi/dl-colab-notebooks
- Owner: tugstugi
- Created: 2019-03-12T20:05:49.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2022-03-10T11:03:40.000Z (almost 3 years ago)
- Last Synced: 2025-01-04T20:04:30.505Z (10 days ago)
- Topics: cnn, colab-notebook, deep-learning, deep-neural-networks, google-colab, google-colaboratory, jupyter-notebook, jupyter-notebooks, pytorch, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 65.7 MB
- Stars: 1,733
- Watchers: 64
- Forks: 464
- Open Issues: 15
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-google-colab - Deep Learning Examples - Try out deep learning models online on Google Colab (Course and Tutorial)
README
Try out deep learning models online on Colab with a single click.
## TTS
* An English female voice ([LJSpeech](https://keithito.com/LJ-Speech-Dataset/)) demo using [NVIDIA/tacotron2](https://github.com/NVIDIA/tacotron2) and [NVIDIA/waveglow](https://github.com/NVIDIA/waveglow) [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/NVidia_Tacotron2_Waveglow.ipynb)
* LibriTTS trained multi speaker TTS demo using [NVIDIA/flowtron](https://github.com/NVIDIA/flowtron)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/NVidia_Flowtron_Waveglow.ipynb)
* An English female voice ([LJSpeech](https://keithito.com/LJ-Speech-Dataset/)) demo using [Rayhane-mamah/Tacotron-2](https://github.com/Rayhane-mamah/Tacotron-2) and [r9y9/wavenet_vocoder](https://github.com/r9y9/wavenet_vocoder)
[](https://colab.research.google.com/github/r9y9/Colaboratory/blob/master/Tacotron2_and_WaveNet_text_to_speech_demo.ipynb)
* A Mongolian male voice demo using [Rayhane-mamah/Tacotron-2](https://github.com/Rayhane-mamah/Tacotron-2) with the Griffin-Lim algorithm
[](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/Tacotron_MongolianTTS.ipynb)
* An English female voice ([LJSpeech](https://keithito.com/LJ-Speech-Dataset/)) demo using [tugstugi/pytorch-dc-tts](https://github.com/tugstugi/pytorch-dc-tts) with the Griffin-Lim algorithm
[](https://colab.research.google.com/github/tugstugi/pytorch-dc-tts/blob/master/notebooks/EnglishTTS.ipynb)
* An English female voice ([LJSpeech](https://keithito.com/LJ-Speech-Dataset/)) demo using [fatchord/WaveRNN](https://github.com/fatchord/WaveRNN) (Tacotron + WaveRNN)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/fatchordWaveRNN.ipynb)
* An English female voice ([LJSpeech](https://keithito.com/LJ-Speech-Dataset/)) demo using [mozilla/TTS](https://github.com/mozilla/TTS) (Tacotron + WaveRNN)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/Mozilla_TTS_WaveRNN.ipynb)
* [NVIDIA/mellotron](https://github.com/NVIDIA/mellotron) notebook
[](https://colab.research.google.com/github/yhgon/mellotron/blob/master/inference_colab.ipynb)
* Voice clone demo using [CorentinJ/Real-Time-Voice-Cloning](https://github.com/CorentinJ/Real-Time-Voice-Cloning)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/RealTimeVoiceCloning.ipynb)
* Official [ESPnet](https://github.com/espnet/espnet) English/Chinese/Japanese TTS notebook [](https://colab.research.google.com/github/espnet/notebook/blob/master/tts_realtime_demo.ipynb)
* Official [ForwardTacotron](https://github.com/as-ideas/ForwardTacotron) LJSpeech TTS notebook [](https://colab.research.google.com/github/as-ideas/ForwardTacotron/blob/master/notebooks/synthesize.ipynb)
## Speech Recognition
* [mozilla/DeepSpeech](https://github.com/mozilla/DeepSpeech) with LM on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/MozillaDeepSpeech.ipynb)
* Wav2Letter+ from [NVIDIA/OpenSeq2Seq](https://github.com/NVIDIA/OpenSeq2Seq.git) without LM on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/NVidiaWav2LetterPlus.ipynb)
* Jasper from [NVIDIA/OpenSeq2Seq](https://github.com/NVIDIA/OpenSeq2Seq.git) without LM on Youtube videos [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/NVidiaJasper.ipynb)
* QuartzNet from [NVIDIA/Nemo](https://github.com/NVIDIA/NeMo.git) without LM on Youtube videos [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/NVidiaQuartzNet.ipynb)
* QuartzNet from [NVIDIA/Nemo](https://github.com/NVIDIA/NeMo.git) without LM with microphone [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/NVidiaQuartzNetMic.ipynb)
* CitriNet from [NVIDIA/Nemo](https://github.com/NVIDIA/NeMo.git) without LM with microphone [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/NVidiaCitriNetMic.ipynb)
* Official [ESPnet](https://github.com/espnet/espnet) Spanish->English speech translation notebook [](https://colab.research.google.com/github/espnet/notebook/blob/master/st_demo.ipynb)
* English/German/Spain Silero speech recognition with [snakers4/silero-models](https://github.com/snakers4/silero-models) [](https://colab.research.google.com/github/snakers4/silero-models/blob/master/examples.ipynb)
## Object Detection
* Tensorflow object detection: FasterRCNN+InceptionResNet and ssd+mobilenet
[](https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/object_detection.ipynb)
* Cascade RCNN demo using [open-mmlab/mmdetection](https://github.com/open-mmlab/mmdetection)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/Open_MMLab_Detection_Toolbox_Cascade_RCNN.ipynb)
* YOLO demo using [ayooshkathuria/pytorch-yolo-v3](https://github.com/ayooshkathuria/pytorch-yolo-v3)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/YOLOv3_PyTorch.ipynb)
* Object detection on Youtube videos using [amdegroot/ssd.pytorch](https://github.com/amdegroot/ssd.pytorch) (SSD300)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/SSD_Pytorch_Video.ipynb)
* Mask RCNN demo using [matterport/Mask_RCNN](https://github.com/matterport/Mask_RCNN)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/Matterport_Mask_RCNN.ipynb)
* Mask RCNN demo using [Detectron](https://github.com/facebookresearch/Detectron)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/Detectron_MaskRCNN.ipynb)
* Official Mask RCNN demo from [Detectron2](https://github.com/facebookresearch/detectron2)
[](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
* Mask RCNN demo from [torchvision](https://pytorch.org/docs/stable/torchvision/index.html)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/TorchvisionMaskRCNN.ipynb)
* CenterNet (Objects as Points) demo using [xingyizhou/CenterNet](https://github.com/xingyizhou/CenterNet)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/CenterNet_ObjectsAsPoints.ipynb)
* CenterNet (Objects as Points) 3D car detection demo using [xingyizhou/CenterNet](https://github.com/xingyizhou/CenterNet) [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/CenterNet_ObjectsAsPoints_3D.ipynb)
* works only on a Kitti image because of camera parameters
* Official DE⫶TR demo notebook [facebookresearch/detr](https://github.com/facebookresearch/detr)
[](https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/detr_demo.ipynb)
* Official Google [EfficientDet](https://arxiv.org/abs/1911.09070) notebook
[](https://colab.research.google.com/github/google/automl/blob/master/efficientdet/tutorial.ipynb)
## Segmentation
* For Mask RCNN, see [Object Detection](https://github.com/tugstugi/dl-colab-notebooks#object-detection)
* Semantic segmentation trained on [ADE20K](http://groups.csail.mit.edu/vision/datasets/ADE20K/) using [CSAILVision/semantic-segmentation-pytorch](https://github.com/CSAILVision/semantic-segmentation-pytorch)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/CSAILVision_SemanticSegmentation.ipynb)
* [DeepLabV3](https://arxiv.org/abs/1706.05587) from [torchvision](https://pytorch.org/docs/stable/torchvision/index.html)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/TorchvisionDeepLabV3.ipynb)
* Fast tracking and segmentation with [SiamMask](https://github.com/foolwood/SiamMask) on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/SiamMask.ipynb)
* Real-time semantic segmentation with [LightNet++](https://github.com/ansleliu/LightNetPlusPlus) on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/LightNetPlusPlus.ipynb)
* Real-time instance segmentation with [YOLACT](https://github.com/dbolya/yolact) on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/YOLACT.ipynb)
* Instance segmentation with [CenterMask](https://github.com/youngwanLEE/CenterMask/)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/CenterMask.ipynb)
## Multi Object Tracking
* Pedestrian tracking using [ZQPei/deep_sort_pytorch](https://github.com/ZQPei/deep_sort_pytorch) (DeepSORT + YOLOv3)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/DeepSORT_YOLOv3.ipynb)
## Pose Detection
* [OpenPose](https://github.com/CMU-Perceptual-Computing-Lab/openpose) on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/OpenPose.ipynb)
* [AlphaPose](https://github.com/MVIG-SJTU/AlphaPose) on Youtube videos
* v0.2.0: [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/AlphaPose.ipynb)
* v0.3.0: [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/AlphaPoseV0_3_0.ipynb)
* [DensePose](https://github.com/facebookresearch/DensePose) demo notebook
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/DensePose.ipynb)
* HRNet using [lxy5513/hrnet](https://github.com/lxy5513/hrnet) on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/HRNet_lxy5513.ipynb)
* Keypoint R-CNN from [torchvision](https://pytorch.org/docs/stable/torchvision/index.html)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/TorchvisionPersonKeypoint.ipynb)
## Scene Text Detection
* [PixelLink](https://github.com/ZJULearning/pixel_link) demo notebook
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/PixelLink.ipynb)
* Scene text detection using [argman/EAST](https://github.com/argman/EAST)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/EAST.ipynb)
* Scene text detection using [CRAFT-pytorch](https://github.com/clovaai/CRAFT-pytorch)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/CRAFT.ipynb)
## GAN
* BigGAN [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://arxiv.org/abs/1809.11096)
[](https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/biggan_generation_with_tf_hub.ipynb)
* [DeOldify](https://github.com/jantic/DeOldify): A Deep Learning based project for colorizing and restoring old images
* deoldify an image [](https://colab.research.google.com/github/jantic/DeOldify/blob/master/ImageColorizerColab.ipynb)
* deoldify a video [](https://colab.research.google.com/github/jantic/DeOldify/blob/master/VideoColorizerColab.ipynb)
* Generates a talking face video from an image and an audio using [Rudrabha/LipGAN](https://github.com/Rudrabha/LipGAN)
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/LipGAN.ipynb)
* PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [](https://colab.research.google.com/github/ctawong/PULSE_from_image_url/blob/master/PULSE_URL.ipynb)
## Misc
* Slow motion using [avinashpaliwal/Super-SloMo](https://github.com/avinashpaliwal/Super-SloMo) on Youtube videos
[](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/SuperSloMo.ipynb)
* Finetune GPT2 [ak9250/gpt-2-colab](https://github.com/ak9250/gpt-2-colab/) [](https://colab.research.google.com/github/ak9250/gpt-2-colab/blob/master/GPT_2.ipynb)
* Music Source Separation [sigsep/open-unmix-pytorch](https://github.com/sigsep/open-unmix-pytorch) [](https://colab.research.google.com/drive/1mijF0zGWxN-KaxTnd0q6hayAlrID5fEQ)
* Image Super Resolution [idealo/image-super-resolution](https://github.com/idealo/image-super-resolution) [](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/ISR_Prediction_Tutorial.ipynb)
* First Order Motion Model for Image Animation [AliaksandrSiarohin/first-order-model](https://github.com/AliaksandrSiarohin/first-order-model) [](https://colab.research.google.com/github/AliaksandrSiarohin/first-order-model/blob/master/demo.ipynb)
* Official notebook of 3D Photography using Context-aware Layered Depth Inpainting [vt-vl-lab/3d-photo-inpainting](https://github.com/vt-vl-lab/3d-photo-inpainting) [](https://colab.research.google.com/drive/1706ToQrkIZshRSJSHvZ1RuCiM__YX3Bz)
* [Image-GPT](https://github.com/openai/image-gpt) notebook [](https://colab.research.google.com/github/apeguero1/image-gpt/blob/master/Image_GPT_Sample_with_Conditioning.ipynb)
* Background Matting: The World is Your Green Screen [senguptaumd/Background-Matting](https://github.com/senguptaumd/Background-Matting) [](https://colab.research.google.com/gist/andreyryabtsev/243aa3eefa6e06891dda7b1583d1d08f/backmatting.ipynb)