ML Datasets

 

Computer Vision

[1] Community https://huggingface.co/datasets

 

ASNetwork : Breaking ambiguity

 

 

[1] Salient Object Detection Driven by Fixation Prediction https://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Salient_Object_Detection_CVPR_2018_paper.pdf

[2] Action Schema Networks https://ipc2023-learning.github.io/abstracts/asnets.pdf

Deep Gan Applications

Super Resolution

[0] https://replicate.com/collections/super-resolution 

[1] https://replicate.com/nightmareai/real-esrgan  /require github account

[2] https://replicate.com/mv-lab/swin2sr (alternative) 

[3] Nightmare https://www.nightmare-ai.com/playground

Styles

[1] https://replicate.com/collections/ml-makeovers 

Restoration

[1] 5byday https://www.restorephotos.io/restore (based on replicate)

[2] https://replicate.com/collections/image-restoration

[3] https://replicate.com/microsoft/bringing-old-photos-back-to-life

 

Alternatives

[1] https://ai.nero.com/photo-restore

[2] https://www.aiease.ai/app/restore-photo

[3] https://photobooth.online/en-us/photo-restoration/upload

[4] https://www.photorestore.io/restore 

[5] https://jpghd.com/

Graph Neural Network - Step 1

 

References:

[1] Short review https://neptune.ai/blog/graph-neural-network-and-some-of-gnn-applications

[2] Coding GNN https://keras.io/examples/graph/gnn_citations/

[2.1] https://keras.io/examples/graph/gat_node_classification/

Rip current detection

 

[1] Correntes de retorno https://www.youtube.com/watch?v=yKvDOzvjApE

[2] Rip Current  https://www.youtube.com/watch?v=RJ4hcaJ91TY

[3] Paper 2021 https://arxiv.org/pdf/2102.02902.pdf

 

CNN Architectures

 

[1] Keras CNN networks with size and time https://keras.io/api/applications/

Deep nostalgia

 

https://time-travel-rephotography.github.io/

https://www.myheritage.com.br/deep-nostalgia

Deep Learning Architectures

[1] Helper using latex to Draw Net https://github.com/HarisIqbal88/PlotNeuralNet

[2] https://github.com/yosinski/deep-visualization-toolbox

[3] https://github.com/wagenaartje/neataptic

[4] .Appimage (viewer .h5 models) https://github.com/lutzroeder/netron

[5] 

!pip install visualkeras
import visualkeras
visualkeras.layered_view(modelobject)

[6] Quiver? https://github.com/ashishpatel26/Tools-to-Design-or-Visualize-Architecture-of-Neural-Network

References:

[1] https://datascience.stackexchange.com/questions/12851/how-do-you-visualize-neural-network-architectures/44571#44571

3D Deep Learning

 

https://github.com/mit-han-lab/pvcnn

https://paperswithcode.com/paper/octnet-learning-deep-3d-representations-at

Segmentation Lectures

https://medium.com/free-code-camp/mask-r-cnn-explained-7f82bec890e3
https://www.analyticsvidhya.com/blog/2019/07/computer-vision-implementing-mask-r-cnn-image-segmentation/

Facial Expression related

[1] Face Drawing http://geometrylearning.com/paper/DeepFaceDrawing.pdf

Automatically Text to speech resources

[1] Text to speech https://github.com/as-ideas/TransformerTTS

Image Segmentation using Deep Learning resources

[1] https://www.nature.com/articles/s41699-020-0137-z.pdf

https://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC5729043&blobtype=pdf

https://borda.github.io/pyImSegm/

http://vision.cs.utexas.edu/projects/keysegments/keysegments.html

Coffee Rust

Based on Deep Learning

[1] Deep Learning for Classification and Severity Estimation of Coffee Leaf BioticStresshttps://arxiv.org/pdf/1907.11561.pdf



Datasets Coffee Rust
[1] Coffe leaves https://github.com/esgario/lara2018/tree/master/classifier
[2] https://www.digipathos-rep.cnptia.embrapa.br/

DeepHuman: Single image to 3D model

Paper https://www.profillic.com/paper/arxiv:1903.06473
Code https://github.com/ZhengZerong/DeepHuman

https://github.com/alexjc/neural-enhance
https://github.com/idealo/image-super-resolution

Machine intelligence

Google brain https://research.google.com/bigpicture/

Interactive Maps and D3 and others

References:
[1] Image to map by Deep Learning https://ai.facebook.com/blog/mapping-roads-through-deep-learning-and-weakly-supervised-training/

Resources

[1] Just a map https://codepen.io/manishgolcha/post/world-map-using-d3-js
[2] Datamaps http://datamaps.github.io/
     Tutorial https://github.com/markmarkoh/datamaps/blob/master/README.md#getting-started

[3] Worldmap by cuntry tooltip http://bl.ocks.org/micahstubbs/8e15870eb432a21f0bc4d3d527b2d14f
[4] d3-zoom https://github.com/d3/d3-zoom


Free geocode
[1] Works using open street map https://opencagedata.com/api
      https://api.opencagedata.com/geocode/v1/json?q=São Paulo&key=8c0e3ccc191e41f38dd211fe50fb9eab

[2] Limited https://developer.here.com/documentation/maps/dev_guide/topics/quick-start.html

[3] Google not recommended https://developers.google.com/maps/documentation/geocoding/intro


Testing
https://blockbuilder.org/Ayumix01/984d70d411ea1d29f48b3963881a5618
 https://medium.com/@ttemplier/map-visualization-of-open-data-with-d3-part3-db98e8b346b3
http://datawanderings.com/2018/10/28/making-a-map-in-d3-js-v-5/
https://github.com/ivan-ha/d3-hk-map

Avatar Lectures

Resources:

[1] Avatar SDK https://avatarsdk.com/
     https://webdemo.avatarsdk.com/
[2] https://neurohive.io/en/state-of-the-art/realistic-3d-avatars-from-a-single-image/
[3] https://neurohive.io/en/computer-vision/head-reconstruction-from-internet-photos/
[4] https://neurohive.io/en/state-of-the-art/learning-3d-face-morphable-model-out-of-2d-images/
[5] https://neurohive.io/en/state-of-the-art/method-for-automatic-forensic-facial-reconstruction/
[6] https://sketchfab.com/
[7] https://www.loomai.com/

Deep Learning Topics 1

References:
[1] Feature Extraction https://keras.io/applications/