#pytorch #pytorch3d #3ddeeplearning #deeplearning #machinelearning

In this video, I try the 3D Deep Learning tutorials from Pytorch 3D. Join me and learn a bit about 3D Deep Learning.

✅ Recommended Courses
(Includes Amazon Affiliate Links)
==================================
⭐ Python for Everybody 👉🏼 https://coursera.pxf.io/mgJKke
⭐ Machine Learning Specialization with Andrew Ng 👉🏼 https://imp.i384100.net/KemLOy
⭐ Learn Data Science with Coursera Plus 👉🏼 https://imp.i384100.net/c/3326428/1320998/14726

✅ Recommended Playlists
==================================
#️⃣ Wildlife Detection with the Raspberry PI 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpA_Jh
#️⃣ Tensorflow Style Transfer Tutorial and Examples 👉 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpDmz2
#️⃣ 3D Deep Learning 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpBPBE
#️⃣ Creating a 3D model of a Photo using Python and Numpy 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpDs8u
#️⃣ Python Problems for Beginners 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpC-fs
#️⃣ Python Bot Development For Beginners 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpBwRE
#️⃣ Web Scraping Projects 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpBUHg
#️⃣ Blender Python API 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpBlVn

✅ My Favorite Tech
(Includes Amazon Affiliate Links)
==================================
💻 Ryzen 5950 and RTX 3090 PC for Gaming And ML 👉🏼 https://amzn.to/3Pz5saF
🖥 Gigabyte RTX 3090 Ti 👉🏼 https://amzn.to/3cxKN8l
🖥 Gigabyte RTX 3080 Ti 👉🏼 https://amzn.to/3BeRZjX
🖥 Gigabyte RTX 3070 Ti 👉🏼 https://amzn.to/3z3ZpUC
🖥 Gigabyte RTX 3060 👉🏼 https://amzn.to/3BmEpLk
👨🏼‍💻 M2 Macbook Pro 8GB 👉🏼 https://amzn.to/3OwPKve
👨🏼‍💻 M2 Macbook Air 8GB 👉🏼 https://amzn.to/3PNA7Ri
📟 Raspberry PI 👉 🏼https://amzn.to/3z4wKyP
📟 Raspberry Pi HQ Camera 👉🏼 https://amzn.to/3BirRVo
🖲 Web Camera 👉🏼 https://amzn.to/3v8inIs
📸 My Camera of Choice 👉🏼 https://amzn.to/3BinAkO
🖥 My Monitor of Choice 👉🏼 https://amzn.to/3z6GQ1U
🏢 Standing Desk 👉🏼 https://amzn.to/3Be5ssg
📗 Deep Learning Must Read 👉🏼 https://amzn.to/3OvbCHI

✅ My RTX 3070 and Ryzen 5900 Machine Learning PC Build
(Includes Amazon Affiliate Links)
=======================================================
#️⃣ Watch My First Deep Learning PC Build 👉🏼 https://youtube.com/playlist?l....ist=PL3OV2Akk7XpBQBa
#️⃣ AMD Ryzen 5900X CPU 👉🏼 https://amzn.to/3z6K9Gm
#️⃣ Gigabyte GeForce RTX 3070 EAGLE OC 8GB Graphics Card 👉🏼 https://amzn.to/3BeWTgM
#️⃣ ASUS ROG Strix X570-E Gaming ATX Motherboard, AMD Socket AM4 👉🏼 https://amzn.to/3PNEJXC
#️⃣ Corsair iCUE H150i PRO XT RGB Liquid CPU Cooler (360mm) 👉🏼 https://amzn.to/3b3w44w
#️⃣ Samsung Nvme 980 pro 2tb 👉🏼 https://amzn.to/3zwYpKd
#️⃣ Crucial Solid State Drive 1TB 👉🏼 https://amzn.to/3J3tBUz
#️⃣ PC Case - Phanteks Eclipse P600S 👉🏼 https://amzn.to/3Pw34BB
#️⃣ Memory - Corsair Vengeance RGB Pro 32GB (2x16GB) DDR4 3600- Black 👉🏼 https://amzn.to/3owSSwA
#️⃣ Power Supply - CORSAIR CX750F RGB - 750 Watt, Fully Modular 👉🏼 https://amzn.to/3ophd7E

✅ MY EQUIPMENT FOR YOUTUBE
(Includes Amazon Affiliate Links)
==================================
📸 Sony Vlog Camera ZV1 👉🏼 https://amzn.to/3BinAkO
🎤 Rode Wireless GO 👉🏼 https://amzn.to/3PNA7AQ
🎤 Sennheiser Mke 400 Mic 👉🏼 https://amzn.to/3aYxvBv
💡 Neewer 3 Packs 530 RGB Led Light 👉🏼 https://amzn.to/3J20wZn
🏢 Manfrotto Variable Friction Arm with Bracket, Super Clamp 👉🏼https://amzn.to/3IZILdr

As an Amazon Associate, I earn a small commission from qualifying purchases on the amazon links above. It costs you nothing but helps me in keeping the content coming.

✅ BUSINESS ENQUIRIES

[email protected]

✅ SUPPORT THE CHANNEL or get MENTORING

http://www.patreon.com/codemental

✅ FOLLOW ME

IG 👉🏼 https://www.instagram.com/codemental/
Blog 👉🏼 https://spltech.co.uk/blog/

✅ Timestamps
0:00 Introduction
1:00 Heterogeneous Batching
1:40 3D Operators
3:56 Differential Renderer
4:33 pytorch3d.datasets
5:54 Google Colab: Deform a source mesh to form a target mesh using 3D loss functions
6:52 Loss functions/regularizers: Chamfer distance, edge loss, laplacian smoonthing, normal consistency
8:58 Using Stochastic Gradient Descent for Optimization loop
13:38 Opening the reconstructed mesh in Blender (Dolphin)
16:00 Trying Pytorch3D's visualization tools for Plotly
22:27 Fit a mesh using Pytorch3D's differential renderer

This video is a part of an online course that provides a comprehensive introduction to practial machine learning methods using MATLAB. In addition to short engaging videos, the course contains interactive, in-browser MATLAB projects.

Complete course is available here: http://bit.ly/2Djmuc3
Learn more about using MATLAB for machine learning: http://bit.ly/2O9Sujp

Get a free product Trial: https://goo.gl/ZHFb5u
Learn more about MATLAB: https://goo.gl/8QV7ZZ
Learn more about Simulink: https://goo.gl/nqnbLeSee What's new in MATLAB and Simulink: https://goo.gl/pgGtod

© 2018 The MathWorks, Inc. MATLAB and Simulink are registered
trademarks of The MathWorks, Inc.
See www.mathworks.com/trademarks for a list of additional trademarks. Other product or brand names maybe trademarks or registered trademarks of their respective holders.

Bayesian Deep Learning and a Probabilistic Perspective of Model Construction
ICML 2020 Tutorial

Bayesian inference is especially compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization. Neural networks are typically underspecified by the data, and can represent many different but high performing models corresponding to different settings of parameters, which is exactly when marginalization will make the biggest difference for accuracy and calibration.

The tutorial has four parts:

Part 1: Introduction to Bayesian modelling and overview (Foundations, overview, Bayesian model averaging in deep learning, epistemic uncertainty, examples)

Part 2: The function-space view (Gaussian processes, infinite neural networks, training a neural network is kernel learning, Bayesian non-parametric deep learning)

Part 3: Practical methods for Bayesian deep learning (Loss landscapes, functional diversity in mode connectivity, SWAG, epistemic uncertainty, calibration, subspace inference, K-FAC Laplace, MC Dropout, stochastic MCMC, Bayes by Backprop, deep ensembles)

Part 4: Bayesian model construction and generalization (Deep ensembles, MultiSWAG, tempering, prior-specification, posterior contraction, re-thinking generalization, double descent, width-depth trade-offs, more!)

Slides: https://cims.nyu.edu/~andrewgw/bayesdlicml2020.pdf
Associated Paper: "Bayesian Deep Learning and a Probabilistic Perspective of Generalization" (NeurIPS 2020)
https://arxiv.org/pdf/2002.08791.pdf


Thanks to Kevin Xia (Columbia) for help in preparing the video.