| Mar. 2020 |
Run PyTorch on TPU and GPU without changing code |
neuNEcN9FK4 |
| Apr. 2020 |
Efficient PyTorch debugging with PyTorch Lightning |
BoiqJSAgPsQ |
| May. 2020 |
Converting from PyTorch to PyTorch Lightning |
QHww1JH7IDU |
| Jun. 2020 |
Overfitting test for deep learning in PyTorch Lightning |
7775X23kGhg |
| Aug. 2020 |
Episode 3: From PyTorch to PyTorch Lightning |
DbESHcCoWbM |
| Aug. 2020 |
Episode 1: Training a classification model on MNIST with PyTorch |
OMDn66kM9Qc |
| Aug. 2020 |
Karpathy's minGPT trained with PyTorch Lightning |
2aJFRQ-v6K8 |
| Aug. 2020 |
Lightning Data Modules |
L---MBeSXFw |
| Aug. 2020 |
SimCLR - Evaluation Protocol |
xNPqjL_aJ8s |
| Aug. 2020 |
SimCLR Implementation- Online fine-tuning |
SgiZO4IRz4U |
| Aug. 2020 |
SimCLR - Implementation in PyTorch / PyTorch Lightning |
p8QFB1CiAoQ |
| Aug. 2020 |
SimCLR - Projection Head |
tnktBNn7ygQ |
| Aug. 2020 |
SimCLR implementation- NT-Xnet Loss |
_1eKr4rbgRI |
| Aug. 2020 |
SimCLR Implementation - Projection Head |
-brxmoHvJBE |
| Aug. 2020 |
SimCLR Data Augmentation Pipeline |
Mrp2ntS2QxI |
| Aug. 2020 |
SimCLR - Training without finetuning |
X1Q7avXUILE |
| Aug. 2020 |
SimCLR - Global batch-normalization |
4wddWrTlLsw |
| Aug. 2020 |
SimCLR paper overview |
a7-qwwAFs_s |
| Aug. 2020 |
SimCLR with PyTorch Lightning- intro |
pDJx8i3jenA |
| Aug. 2020 |
Self Supervised Learning |
uX1TT10NpBI |
| Aug. 2020 |
SimCLR Training Hyper Parameters |
OG__SUjIiDk |
| Aug. 2020 |
SimCLR - Tensorboard Visualization with PyTorch Lightning |
hJP_DgZupnQ |
| Sep. 2020 |
Episode 2: PyTorch Dropout, Batch size and interactive debugging |
vD5iQkdqMqU |
| Oct. 2020 |
How to convert from PyTorch into PyTorch Lightning |
grbaIxHyQsI |
| Oct. 2020 |
Training on multiple GPUs and multi-node training with PyTorch DistributedDataParallel |
a6_pY9WwqdQ |
| Oct. 2020 |
Training on TPUs |
Pl6tzT7Fn4s |
| Oct. 2020 |
3 lines of code conversational AI with NVIDIA NeMo and PyTorch Lightning |
0XbX5QCRKFs |
| Oct. 2020 |
Mixed Precision Training |
RJO05tlGQAI |
| Oct. 2020 |
Debugging Lightning Flags |
8q4ieMG1QKU |
| Nov. 2020 |
Accumulating Gradients |
pk1l3pWhFSM |
| Nov. 2020 |
Exploding And Vanishing Gradients |
YZ-vJ2phDCo |
| Nov. 2020 |
SwAV Loss Deep Dive |
M_DgS3XGeJc |
| Nov. 2020 |
SwAV PyTorch Lightning Implementation |
5irer8A2HoY |
| Nov. 2020 |
Self-Supervised Learning of Image Features with SwAV (with author Mathilde Caron) |
7QmsTleiRLs |
| Nov. 2020 |
Episode 4: Implementing a PyTorch Trainer: PyTorch Lightning Trainer and callbacks under-the-hood |
tgp56S2eGFE |
| Dec. 2020 |
Converting from pytorch to pytorch lightning in 4 minutes |
uHMG2XngNYQ |
| Dec. 2020 |
[Virtual Community Meetup] December Lightning Talks |
MjURy6Ow5D8 |
| Dec. 2020 |
Sharded Training |
WLGM08Xd51k |
| Jan. 2021 |
Self-Supervised Learning for Object Detection |
Q4K7njQJKM8 |
| Jan. 2021 |
Training SimCLR and SwAV on Imagenet |
bG-fU5gKYAg |
| Jan. 2021 |
Lightning Chat with NeMo's Research Scientist |
_QksvmLKvks |
| Jan. 2021 |
Creating a Training Pipeline with PyTorch Lightning and Hydra |
w10WrRA-6uI |
| Jan. 2021 |
Lightning Chat: How a Grandmaster Won a Kaggle Competition Using Pytorch Lightning |
0HQCK_l-njI |
| Jan. 2021 |
Event-Based Monocular Human Pose Estimation |
nIS7aZyCj0U |
| Mar. 2021 |
PyTorch Lightning Community Talks - Episode 1 |
WUb0pVJy7iQ |
| Mar. 2021 |
PyTorch Lightning Community Talks - Episode 2 |
p3cARpnelqE |
| Mar. 2021 |
PyTorch Lightning Community Talks - Episode 3 |
owZzNZjdpU8 |
| Mar. 2021 |
PyTorch Lightning Community Talks - Episode 4 |
MNZcoCR05dk |
| Apr. 2021 |
PyTorch Lightning Community Talks - Episode 5 |
svtgCFxE15Y |
| Apr. 2021 |
NVIDIA GTC '21: Half The Memory with Zero Code Changes: Sharded Training with Pytorch Lightning |
w_CKzh5C1K4 |
| May. 2021 |
Grid AI in 3 minutes - Run pytorch, tensorflow, lightning, keras on cloud GPUs and CPUs |
Wm1jjaQzPf0 |
| May. 2021 |
PyConIL 2021 - From Research to Production, Minus the Boilerplate |
GMRGTmQHzhA |
| May. 2021 |
Webinar 4/13/21 - Latest Innovations with PyTorch Lightning |
cFPeVsJLEeU |
| May. 2021 |
Lightning Community Talks Ep 6 Modeling Deep Learning Models for Tabular Data with PyTorch Lightning |
CjU3VxoKjHY |
| May. 2021 |
PyTorch Lightning Training Intro |
gUF6WUq0Cf4 |
| May. 2021 |
Controlling Lightning Training and Eval Loops |
d1zBG_IVKAo |
| May. 2021 |
Lightning Weights Summary |
F860p-oUs0w |
| May. 2021 |
Lightning Profiler |
firBMhnBI-Y |
| May. 2021 |
PyTorch Lightning - Reload DataLoaders Every Epoch |
IdcO1CXbNx4 |
| May. 2021 |
PyTorch Lightning Callbacks |
YzqjvW8-bKk |
| May. 2021 |
Lightning Early Stopping |
vfB5Ax6ekHo |
| May. 2021 |
PyTorch Lightning - Automatic Learning Rate Finder |
cLZv0eZQSIE |
| May. 2021 |
PyTorch Lightning - Automatic Batch Size Finder |
KlK7VVdzsSI |
| Jun. 2021 |
PyTorch Lightning - Accelerator |
55fHcXNBkEY |
| Jun. 2021 |
PyTorch Lightning - Accumulate Grad Batches |
c-7TM6pre8o |
| Jun. 2021 |
PyTorch Lightning - amp backend |
fq7gAacJirQ |
| Jun. 2021 |
PyTorch Lightning - Finding the best learning rate for your model |
WMp-Fu2mlj8 |
| Jun. 2021 |
Lightning Community Talks - Episode 8 |
AfTLsjvgo-M |
| Jun. 2021 |
PyTorch Lightning - Configuring Averaged Mixed Precision |
Qtha1Pny44U |
| Jun. 2021 |
PyTorch Lightning - Auto select GPUs |
38hgdpuziMk |
| Jun. 2021 |
PyTorch Lightning - Speed up model training with benchmark |
OI3Pt1NBzJM |
| Jun. 2021 |
PyTorch Lightning - Ensure reproducibility with deterministic = True |
_GHh_PZGTH4 |
| Jul. 2021 |
PyTorch Lightning - Check val split every n epochs |
2MJGwcXDBb4 |
| Jul. 2021 |
PyTorch Lightning - Debugging with fast dev run |
GrsUSONYShA |
| Jul. 2021 |
PyTorch Lightning - flush logs every n steps |
bY3KkP6HbiI |
| Jul. 2021 |
PyTorch Lightning - Configuring Multiple GPUs |
h27whj6W1pM |
| Jul. 2021 |
PyTorch Lightning - Managing Exploding Gradients with Gradient Clipping |
9rZ4dUMwB2g |
| Jul. 2021 |
PyTorch Lightning - Understanding Precision Training |
d-2EHvJX03Y |
| Jul. 2021 |
PyTorch Lightning - Sanity Checking Your Auto With Overfit Batches |
RxvsvXTQstw |
| Aug. 2021 |
PyTorch Lightning - Smoother Notebook Training With Progress Bar Refresh Rate |
-XakoRiMYCg |
| Aug. 2021 |
PyTorch Lightning - Customizing a Distributed Data Parallel (DDP) Sampler |
mIyy0YVA2-k |
| Aug. 2021 |
PyTorch Lightning - Simple Truncated Back Propagation Through Time |
bYi8gDGCyvg |
| Aug. 2021 |
PyTorch Lightning - Identifying Vanishing and Exploding Gradients with Track Grad Norm |
c8A1f_9hYOg |
| Aug. 2021 |
PyTorch Lightning - Training with TPUs |
eBZciVDr21o |
| Aug. 2021 |
PyTorch Lightning - sync batchnorm |
C-5TsrRCcMI |
| Aug. 2021 |
PyTorch Lightning - val check interval |
oUJsT-WSsM4 |
| Sep. 2021 |
PyTorch Lightning - process position |
z-vAn8BLIcY |
| Sep. 2021 |
PyTorch Lightning - prepare data per node |
ij9z3ob0KSk |
| Sep. 2021 |
PyTorch Lightning - num sanity val steps |
gPD2AXbSuks |
| Sep. 2021 |
PyTorch Lightning - min max epochs |
GVCvr0b2MVM |
| Sep. 2021 |
PyTorch Lightning - min max steps |
ffSU69irIuQ |
| Oct. 2021 |
PyTorch Lightning - limit batches |
2ODZEOvRPUs |
| Oct. 2021 |
PyTorch Lightning - auto scale batch size |
HkKyLE1IBFM |
| Dec. 2021 |
Contributor Meetup: PyTorch Lightning Flash - Your PyTorch AI Factory |
8OQlBBMVEGU |
| Jan. 2022 |
Twitch Live Coding - Make Your First Contribution to PyTorch Lightning |
vhmeebXjuF8 |
| Jan. 2022 |
Twitch Live Coding - Learn How The PyTorch Lightning CI Works |
fjjiT4hzQEw |
| Feb. 2022 |
PyTorch Lightning - Fault Tolerant Dive In |
-HRh_szyuhE |
| Feb. 2022 |
Twitch Live Coding - Learn How to Make your First Lightning Flash Contribution |
nHyC8hwngEI |
| Feb. 2022 |
Twitch Live Coding - Lightning Code Base Hardcore Deep Dive |
aEeh9ucKUkU |
| Mar. 2022 |
Twitch Live Coding: Deep Dive into a Single Example Code Flow |
NEpRYqdsm54 |
| Mar. 2022 |
Twitch Live Coding - Part 3 Lightning Codebase Deep Dive |
x4d4RDNJaZk |
| Apr. 2022 |
PyTorch Lightning Live: Session 1 - Upgrade your Code to v1.6 |
Tblw9UGmMjg |
| Apr. 2022 |
PyTorch Lightning Live: Session 2 - The Benefits of Bagua |
bHxwtJZX7Vc |
| Apr. 2022 |
PyTorch Lightning Live: Session 3 - Fault tolerance |
aUtn7H1jYl4 |
| Apr. 2022 |
PyTorch Lightning Session 4 - Supercharge Your Training With The Habana Accelerator |
BQJTfOhxeIc |
| May. 2022 |
PyTorch Lightning Live: Session 5 - Highlights of PyTorch Lightning v1.6 | Additional features |
TDAP5wYQk4s |
| May. 2022 |
Essential Beginner Computer Science Skills in 10 Mins or Less |
-c55LCTdD90 |
| May. 2022 |
The 8 Essential Terminal Commands you Need to Know | Ep 2 |
KhQKqaxU7BQ |
| May. 2022 |
Jupyter notebooks vs Python projects: Learn when when to use which | Ep 1 |
JGnoTN1OnWY |
| May. 2022 |
How to Use Virtual Environments to Keep Your Computer Organized | Ep 3 |
WHWsABk4Ejk |
| Jun. 2022 |
How to Be More Productive Using Python Integrated Development Environments (IDEs) | Ep 4 |
ISGNh4B1Z74 |
| Jun. 2022 |
How to Debug Python Code -- Find Errors More Efficiently | Ep 5 |
mD-1OZvuVDU |
| Jun. 2022 |
Lightning DevCon Keynote Livestream |
58qpOxKRzqY |
| Jun. 2022 |
Devcon Livestream |
DQZ3_XhdesA |
| Jun. 2022 |
Lightning AI: Build end-to-end ML systems with plain python |
vFwHl7W5ooE |
| Jun. 2022 |
Version Control Your Code Using Git ... And Thank Yourself Later | Ep 6 |
mndB6zHmU3k |
| Jun. 2022 |
Managing Code Projects with Git Branching | Ep 7 |
tzJDZY1x31I |
| Jul. 2022 |
Creating a Pull Request on GitHub | Ep 8 |
_0X_dljzr5E |
| Jul. 2022 |
Collaborate on Coding Projects with GitHub | Ep 9 |
7wb2wUMrkkE |
| Jul. 2022 |
Level-Up Your Python Skills Using Classes and Object-Oriented Programming Concepts | Ep 10 |
rf8da4pVLwY |
| Aug. 2022 |
Build an Interactive Research Poster with Lightning AI |
RbU0CROL8TM |
| Oct. 2022 |
Build an Intelligent App In Weeks, Not Months | Lightning AI |
CWfmJlkfST4 |
| Oct. 2022 |
Hacktoberfest 2022 with Lightning AI |
TbjZ8z51QnQ |
| Oct. 2022 |
Build Tailored Machine Learning Applications |
BcCjJZCud5w |
| Oct. 2022 |
Stable Diffusion Explained and Demystified with Daniela Dapena - Lightning AI |
AQrMWH8aC0Q |
| Oct. 2022 |
How to Deploy Diffusion Models |
JV4Yb-IIEcI |
| Nov. 2022 |
Run your own stable diffusion (2.0) server in 5 minutes. |
Xb7ucqIjjE4 |
| Dec. 2022 |
Deep Learning Fundamentals with Sebastian Raschka - A New Educational Course from Lightning AI |
eggx0GrdYbM |
| Jan. 2023 |
The AI Buzz, Episode #1: ChatGPT, Transformers and Attention |
8_eJCCgfDbE |
| Jan. 2023 |
How To Scale Model Serving in Production |
69PJaWhJsXE |
| Feb. 2023 |
Building ML Pipelines Like Legos with Scikit-Learn and Lightning AI |
4iLUKE3TazY |
| Feb. 2023 |
Boltus: God of AI | Episode 4 |
Bax4n2xXB8w |
| Feb. 2023 |
Boltus: God of AI | Episode 3 |
3tsjTiUFNQc |
| Feb. 2023 |
Boltus: God of AI | Episode 2 |
vWJMqCgTkUk |
| Feb. 2023 |
Boltus: God of AI | Episode 1 |
kpE6Q0cdp3c |
| Feb. 2023 |
Boltus: God of AI | Ep 2 #shorts |
HAUZD3kk3l0 |
| Feb. 2023 |
Boltus: God of AI | Ep 1 #shorts |
M_R99LXPnFU |
| Feb. 2023 |
Boltus: God of AI | Ep 3 #shorts |
hR_0SLd7O8U |
| Feb. 2023 |
Boltus: God of AI | Ep 4 #shorts |
f-NDJ42UQAU |
| Mar. 2023 |
The AI Buzz | GPT4, AI Transforming Business, the Future of Applications | S2, E1 |
YxxPrbumc8s |
| Apr. 2023 |
PyTorch Unleashed: Tips for Lightning Fast LLMs with Taylor Robie |
qRZrVNNe3gQ |
| May. 2023 |
Building Generative Interfaces |
jIHDQNWoMjA |
| May. 2023 |
The AI Buzz | Opensource Licensing for LLMs | S2, E2 |
LXjddn2AvPA |
| May. 2023 |
Fireside Chat: LLaMA Adapter |
XVH6arAHfIU |
| Jun. 2023 |
Lightning AI & Stability AI Event - #Keep AI Open Source |
dEmK-2K4Zhc |
| Jul. 2023 |
Unit 4.3 | Training a Multilayer Perceptron in PyTorch | Part 3 |
1LGkjcAtt8E |
| Jul. 2023 |
Unit 4.4 | Defining Efficient Data Loaders | Part 3 | Coding |
DBWjUvC6xrw |
| Jul. 2023 |
Unit 4.2 | Multilayer Neural Networks | Part 2 | The Multilayer Perceptron Architecture |
RLZBTP4tSSc |
| Jul. 2023 |
Unit 4.3 | Training a Multilayer Perceptron in PyTorch | Part 1 |
XNi5TPSxmZA |
| Jul. 2023 |
Unit 4.1 | Logistic Regression for Multiple Classes | Part 2 | The Softmax Activation Function |
ZVN5jHSfoKA |
| Jul. 2023 |
Unit 4.4 | Defining Efficient Data Loaders | Part 2 | Datasets and Dataloaders |
qQYt36NnTIw |
| Jul. 2023 |
Unit 4.3 | Training a Multilayer Perceptron in PyTorch | Part 4 |
OzQ6jo54rtM |
| Jul. 2023 |
Unit 4.3 | Training a Multilayer Perceptron in PyTorch | Part 5 |
jrPTiNgHj5s |
| Jul. 2023 |
Unit 4.2 | Multilayer Neural Networks | Part 3 | Basic Architecture Design Considerations |
_5BZBQw7_6I |
| Jul. 2023 |
Unit 4.2 | Multilayer Neural Networks | Part 1 | Looking Beyond Linear Decision Boundaries |
Rp88kkUquYM |
| Jul. 2023 |
Unit 4.1 | Logistic Regression for Multiple Classes | Part 4 | Cross Entropy Loss Function |
sfAYY6OQCRk |
| Jul. 2023 |
Unit 4.6 | Speeding Up Model Training Using GPUs |
Xm4nIYbWpnw |
| Jul. 2023 |
Unit 4.1 | Logistic Regression for Multiple Classes | Part 5 | The Cross Entropy Loss Function |
hFwEoYXnnoQ |
| Jul. 2023 |
Unit 4.4 | Defining Efficient Data Loaders | Part 1 | Avoiding Data Loading Bottlenecks |
g-OtQSXohhE |
| Jul. 2023 |
Unit 4.4 | Defining Efficient Data Loaders | Part 4 | Coding |
juLbO2p2Mzc |
| Jul. 2023 |
Unit 5.2 | Training a Multilayer Perceptron in PyTorch Lightning | Part 1 |
DxALtmlxQ4U |
| Jul. 2023 |
Unit 6.6 | Improving Convergence with Batch Normalization | Part 2 | Using BatchNorm in PyTorch |
hQcLc2DjKk0 |
| Jul. 2023 |
Unit 5.4 | Making Code Reproducible | Part 3 | Coding |
nDsh2uw89M8 |
| Jul. 2023 |
Unit 5.1 | Getting Started with Structuring Your PyTorch Code using Lightning |
D1aYLlbfC14 |
| Jul. 2023 |
Unit 7.1 | Working with Images | Part 2 | Image Data and Its Challenges |
fRRq_oLo0N4 |
| Jul. 2023 |
Unit 6.2 | Learning Rates and Learning Rate Schedulers | Part 1 | Finding a Good Learning Rate |
VynjEl-4MYM |
| Jul. 2023 |
Unit 6.2 | Learning Rates and Learning Rate Schedulers | Part 2 |
xKXG0t0_wSo |
| Jul. 2023 |
Unit 5.5 | Organizing Your Data Loaders with Data Modules | Part 2 |
kLiVdwPMqHk |
| Jul. 2023 |
Unit 6.7 | Reducing Overfitting with Dropout | Part 2 | Applying Dropout During Inference |
7_KPDZQfRhs |
| Jul. 2023 |
Unit 5.5 | Organizing Your Data Loaders with Data Modules | Part 1 |
ejXYUte4q3U |
| Jul. 2023 |
Unit 6.2 | Learning Rates and Learning Rate Schedulers | Part 5 |
WgwBRqhdIrQ |
| Jul. 2023 |
Unit 6.8 | Debugging Deep Neural Networks | Part 3 |
Xt2d9JEzVBE |
| Jul. 2023 |
Unit 5.3 | Computing Metrics Efficiently with TorchMetrics | Part 1 | How Does TorchMetrics Work? |
X5qba7W-liw |
| Jul. 2023 |
Unit 5.3 | Computing Metrics Efficiently with TorchMetrics | Part 3 |
QSLoBmYSytY |
| Jul. 2023 |
Unit 7 | Getting Started with Computer Vision |
H8mCQMtFv_0 |
| Jul. 2023 |
Unit 6.3 | Using More Advanced Optimization Algorithms | Part 1 | Using Momentum to Nudge SGD |
p_0aZx1wZWU |
| Jul. 2023 |
Unit 6.2 | Learning Rates and Learning Rate Schedulers | Part 3 |
WXK7JBf0pso |
| Jul. 2023 |
Unit 6.1 | Model Checkpointing and Early Stopping | Part 1 |
9Vc7tTWZark |
| Jul. 2023 |
Unit 5.7 | Evaluating and Using Models on New Data | Part 1 | Fundamental Model Inspection Steps |
HXO2YwMhhOQ |
| Jul. 2023 |
Unit 5.6 | The Benefits of Logging | Part 2 | Coding |
uZnbgG6KvZQ |
| Jul. 2023 |
Unit 5.6 | The Benefits of Logging | Part 1 | Tracking Training Progress |
d9mQRKLTV5o |
| Jul. 2023 |
Unit 4.5 | Multilayer Neural Networks for Regression | Part 2 | Coding |
vlU812sgNmA |
| Jul. 2023 |
Unit 6.4 | Choosing Activation Functions |
8wjiF2au9nk |
| Jul. 2023 |
Unit 6.8 | Debugging Deep Neural Networks | Part 2 |
OhoOILdrNEI |
| Jul. 2023 |
Unit 6.8 | Debugging Deep Neural Networks | Part 1 |
Dgrb9jfFuck |
| Jul. 2023 |
Unit 5.2 | Training a Multilayer Perceptron in PyTorch Lightning | Part 2 |
Y11-leJtC1k |
| Jul. 2023 |
Unit 5.4 | Making Code Reproducible | Part 2 | Controlling Sources of Randomness |
5yo58Z9zUl0 |
| Jul. 2023 |
Unit 5 | Organizing Your PyTorch Code with Lightning |
x4UvpMsyG8M |
| Jul. 2023 |
Unit 5.7 | Evaluating and Using Models on New Data | Part 2 |
9oTXQEco69g |
| Jul. 2023 |
Unit 7.2 | How Convolutional Networks Work | Part 2 | Convolutional Layers |
DH6L-gU3ZI4 |
| Jul. 2023 |
Unit 5.3 | Computing Metrics Efficiently with TorchMetrics | Part 2 |
ijOa3vxY2lI |
| Jul. 2023 |
Unit 8.3 | Introduction to Recurrent Neural Networks | Part 4 | Embedding Layers in PyTorch |
YJdO7er_8k8 |
| Jul. 2023 |
Unit 7.3 | Convolutional Neural Network Architectures | Part 2 | CNNs and Their Inception(s) |
5sdnqI_gc3w |
| Jul. 2023 |
Unit 8.5 | Understanding Self-Attention | Part 1 | A Basic Attention Mechanism |
6JZoX4nbkrQ |
| Jul. 2023 |
Unit 8.4 | From RNNs to the Transformer Architecture | Part 1 | Introducing Transformers |
3ynQmZwFea4 |
| Jul. 2023 |
Unit 7.6 | Leveraging Pretrained Models with Transfer Learning | Part 2 |
aonvyGU94JE |
| Jul. 2023 |
Unit 7.2 | How Convolutional Networks Work | Part 4 | What are Pooling Layers? |
MtonqE5-FMo |
| Jul. 2023 |
Unit 8.5 | Understanding Self-Attention | Part 2 | Self-Attention with Learnable Weights |
EuJ7gTMoskQ |
| Jul. 2023 |
Unit 7.7 | Using Unlabeled Data with Self-Supervised Learning | Part 4 |
f2liRhsiaOw |
| Jul. 2023 |
Unit 7.5 | Data Augmentation | Part 2 | Implementing Data Augmentations in PyTorch |
DY905WdWv_M |
| Jul. 2023 |
Unit 8.1 | Working with Text Data | Part 1 | Text Modeling Considerations |
TeOX4UVL9DQ |
| Jul. 2023 |
Unit 7.4 | Training CNNs | Part 1 | An MLP Baseline |
VghIoU1uA1Q |
| Jul. 2023 |
Unit 7.7 | Using Unlabeled Data with Self-Supervised Learning | Part 5 |
xZ8K_nVA5Mg |
| Jul. 2023 |
Unit 7.7 | Using Unlabeled Data with Self-Supervised Learning | Part 1 |
vFREtWTIkXA |
| Jul. 2023 |
Unit 8.2 | Training a Bag-of-Words Based Classifier | Part 2 |
uEZMhR6we_I |
| Jul. 2023 |
Unit 7.6 | Leveraging Pretrained Models with Transfer Learning | Part 1 |
EwvbdSM1CNQ |
| Jul. 2023 |
Unit 8.3 | Introduction to Recurrent Neural Networks | Part 3 | Encoding Inputs w/ Embedding Layers |
MuBuHLIK8hE |
| Jul. 2023 |
Unit 8.3 | Introduction to Recurrent Neural Networks | Part 1 | Modeling Sequence Data |
gkXxnHzFt0Q |
| Jul. 2023 |
Unit 8.2 | Training a Bag-of-Words Based Classifier | Part 1 |
WqpBCmyKmXE |
| Jul. 2023 |
Unit 7.6 | Leveraging Pretrained Models with Transfer Learning | Part 3 |
uflSD_SDNsk |
| Jul. 2023 |
Unit 7.7 | Using Unlabeled Data with Self-Supervised Learning | Part 3 | SimCLR |
RRKNSSfqb1Y |
| Jul. 2023 |
Unit 7.5 | Data Augmentation | Part 1 | Concepts and Examples |
V5bRNVj5Ywo |
| Jul. 2023 |
Unit 7.3 | Convolutional Neural Network Architectures | Part 1 | The Main Ideas |
jjjrl6FCL7E |
| Jul. 2023 |
Unit 7.4 | Training CNNs | Part 4 | Training a ResNet on CIFAR |
AkZc3but4jA |
| Jul. 2023 |
Unit 8.4 | From RNNs to the Transformer Architecture | Part 2 | Why Do We Need Attention? |
vRt9NFaRz_8 |
| Jul. 2023 |
Unit 7.4 | Training CNNs | Part 5 | Loading a ResNet from Torchvision Hub |
QQcDWiV59aU |
| Jul. 2023 |
Unit 7.7 | Using Unlabeled Data with Self-Supervised Learning | Part 2 |
9w-9Sgs_8YQ |
| Jul. 2023 |
Unit 8.3 | Introduction to Recurrent Neural Networks | Part 2 | Different Sequence Modeling Tasks |
biBeJMwPnYM |
| Jul. 2023 |
Unit 9.5 | Increasing Batch Sizes to Increase Throughput | Part 2 | Code Demo |
-50SEU-j6uI |
| Jul. 2023 |
Unit 10.1 | Trustworthy and Reliable Machine Learning | Part 1 | Important ML Considerations |
-d5sGU5jYU0 |
| Jul. 2023 |
Unit 10.3 | Designing Machine Learning Systems |
JF0beAHXo0o |
| Jul. 2023 |
Unit 9.5 | Increasing Batch Sizes to Increase Throughput | Part 1 | Are Large Batch Sizes Better? |
Rlebpaz4SNs |
| Jul. 2023 |
Unit 9.3 | Deep Dive into Data Parallelism | Part 2 | Distributed Data Parallelism |
RltaQ-HxqKE |
| Jul. 2023 |
Unit 9.3 | Deep Dive into Data Parallelism | Part 3 | Multi-GPU Hands-On Code Demo |
UryUT5LypRc |
| Jul. 2023 |
Unit 9.2 | Multi-GPU Training Strategies | Part 2 | Choosing a Multi-GPU Strategy |
eEKXC2Oti8A |
| Jul. 2023 |
Unit 1.1 | What is Machine Learning? | Part 2 | How does it relate to deep learning? |
GRwA34olQDU |
| Jul. 2023 |
Unit 1.4 | The First Machine Learning Classifier | Part 2 | Making Predictions |
mSOcAugf6aI |
| Jul. 2023 |
Unit 1.2 | How Can We Use Machine Learning? | Part 1 | Common Application Areas |
CGKnJwE8vB0 |
| Jul. 2023 |
Unit 10.4 | Deep Learning Fundamentals Conclusion |
XvP5hVK9E0I |
| Jul. 2023 |
Unit 8.5 | Understanding Self-Attention | Part 4 | Masked Attention and Positional Encoding |
5JfnnzUfqg8 |
| Jul. 2023 |
Unit 1.4 | The First Machine Learning Classifier | Part 1 | Defining the Prediction Task |
JUI9Gz_VzEo |
| Jul. 2023 |
Unit 9.2 | Multi-GPU Training Strategies | Part 1 | Introduction to Multi-GPU Training |
NmoDg5PPDQY |
| Jul. 2023 |
Unit 8.6 | Large Language Models | Part 1 | The Two Main Ingredients |
VGMQcFB5YX4 |
| Jul. 2023 |
Unit 9 | Techniques for Speeding Up Model Training |
uqYrVdlXkz8 |
| Jul. 2023 |
Unit 10.1 | Trustworthy and Reliable Machine Learning | Part 2 | Constructing Confidence Intervals |
eqf6-WGpgx8 |
| Jul. 2023 |
Unit 1.4 | The First Machine Learning Classifier | Part 3 | The Training Process |
qiKfvE1VUu0 |
| Jul. 2023 |
Unit 9.4 | Compiling PyTorch Models | Part 2 | Code Demo |
6jjaLlgSYJg |
| Jul. 2023 |
Unit 8.7 | A Large Language Model for Classification | Part 1 | Bidirectional Pertaining with BERT |
Sd_q_2pTuP4 |
| Jul. 2023 |
Unit 1.2 | How Can We Use Machine Learning? | Part 2 | The Three Classic Categories |
ltCYDQGwIP4 |
| Jul. 2023 |
Unit 9.3 | Deep Dive into Data Parallelism | Part 1 | Understanding Data Parallelism |
MNdRsINYtRE |
| Jul. 2023 |
Unit 10.2 | Fabric - Scaling PyTorch Models without Boilerplate Code | Part 1 |
4ZH5ey6r7F0 |
| Jul. 2023 |
Unit 9.4 | Compiling PyTorch Models | Part 1 | Understanding Static and Dynamic Graphs |
6ZElb2W_i5Y |
| Jul. 2023 |
Unit 9.1 | Accelerated Model Training via Mixed-Precision Training | Part 1 |
3SK_tFAcUP8 |
| Jul. 2023 |
Unit 8.7 | A Large Language Model for Classification | Part 3 |
H4s9nToUGkw |
| Jul. 2023 |
Unit 3.5 | The PyTorch API | Part 1 | Model Training |
-C0fAxFj67M |
| Jul. 2023 |
Unit 2.4 | Improving Code Efficiency with Linear Algebra | Part 2 | Matrix Multiplications |
bc5IpN6bCjU |
| Jul. 2023 |
Unit 3.5 | The PyTorch API | Part 2 | Neural Network Layers |
4SOokqvnJjc |
| Jul. 2023 |
Unit 3.3 | Model Training with Stochastic Gradient Descent | Part 4 |
Zp60oKbR1UY |
| Jul. 2023 |
Unit 1.4 | The First Machine Learning Classifier | Part 4 | Perceptron Training by Example |
nlIpS3NLWgc |
| Jul. 2023 |
Unit 3.6 | Training a Logistic Regression Model in PyTorch | Part 1 |
5XL-FdlsRqg |
| Jul. 2023 |
Unit 2.6 | Revisitng Perceptron Tensors |
7jQu4q6MYNU |
| Jul. 2023 |
Unit 2.1 | Introducing PyTorch |
9V1-G9bA4Dw |
| Jul. 2023 |
Unit 3 | Model Training in PyTorch |
-tkVHRCEjlc |
| Jul. 2023 |
Unit 1.4 | The First Machine Learning Classifier | Part 5 | Weight Updates |
1J_P8NLvnIA |
| Jul. 2023 |
Unit 2.5 | Debugging Code |
Iq_jr8Q8iz8 |
| Jul. 2023 |
Unit 3.1 | Using Logistic Regression for Classification | Part 1 | Single Layer Neural Networks |
URK12kJCJSc |
| Jul. 2023 |
Unit 1.7 | Evaluating Machine Learning Models | Part 2 | Performance Metrics for Model Evaluation |
haRknoDU90Q |
| Jul. 2023 |
Unit 3.3 | Model Training with Stochastic Gradient Descent | Part 1 |
pKKiX08HLko |
| Jul. 2023 |
Unit 1.6 | Perceptron in Python | Part 3| Coding Example |
YF9p8TKzmRM |
| Jul. 2023 |
Unit 1.4 | The First Machine Learning Classifier | Part 6 | Perceptron Decision Boundary |
pGHwdf54mrY |
| Jul. 2023 |
Unit 2.3 | How Do We Use Tensors in PyTorch? |
7qtZry76UfY |
| Jul. 2023 |
Unit 3.2 | The Logistic Regression Computation Graph |
zvZ4VqITAOA |
| Jul. 2023 |
Unit 2.7 | Seeing Predictive Models as Computation Graphs |
YjhjEm8DTRM |
| Jul. 2023 |
Unit 2 | First Steps with PyTorch: Using Tensors |
28M8l9EFJck |
| Jul. 2023 |
Unit 3.3 | Model Training with Stochastic Gradient Descent | Part 2 |
3VL_k7RJ0nQ |
| Jul. 2023 |
Unit 3.1 | Using Logistic Regression for Classification | Part 2 | Logistic Sigmoid Function |
JvoHfm-WkV8 |
| Jul. 2023 |
Unit 1.7 | Evaluating Machine Learning Models | Part 1 | Using Validation Sets |
PmKGsTGz_UQ |
| Jul. 2023 |
Unit 10 | The Finale: Our Next Steps After AI Model Training |
YwxJP7J-Z7A |
| Jul. 2023 |
Unit 6.7 | Reducing Overfitting with Dropout | Part 1 | The Main Idea Behind Dropout |
CbMlFGzpFkQ |
| Jul. 2023 |
Truncated Back-propogation Through Time |
2K_jUv8aKN4 |
| Jul. 2023 |
Unit 1.3 | A Typical Machine Learning Workflow |
cIt04Sh0oyg |
| Jul. 2023 |
Unit 8 | Introduction to Natural Language Processing and Large Language Models |
RAS7DgGYZvU |
| Jul. 2023 |
Unit 2.4 | Improving Code Efficiency with Linear Algebra | Part 1 | From For-Loops to Dot Products |
DKYIjPVzsoE |
| Jul. 2023 |
Unit 7.4 | Training CNNs | Part 3 | Introducing the CIFAR Dataset |
f2TPkYLsHRk |
| Jul. 2023 |
Unit 7.2 | How Convolutional Networks Work | Part 3 | Convolutions with Multiple Channels |
Xn2sLlFTY5k |
| Jul. 2023 |
Unit 6.6 | Improving Convergence with Batch Normalization | Part 1 | Scaling Layer Inputs |
LvYBg1gBEU4 |
| Jul. 2023 |
Unit 6.2 | Learning Rates and Learning Rate Schedulers | Part 4 | Annealing the Learning Rate |
LVXsXe8IU0Q |
| Jul. 2023 |
Unit 8.5 | Understanding Self-Attention | Part 3 | From Self-Attention to Multi-Head Attention |
EfzWHVbp_m4 |
| Jul. 2023 |
Unit 6.3 | Using More Advanced Optimization Algorithms | Part 2 | Adaptive Learning Rates |
zl4NtWG15y8 |
| Jul. 2023 |
Unit 1.6 | Perceptron in Python | Part 1| Coding Example |
ftzkrT82tlI |
| Jul. 2023 |
Unit 7.2 | How Convolutional Networks Work | Part 5 | Controlling the Output Size with Padding |
CgUrP8FlHxM |
| Jul. 2023 |
Unit 6.7 | Reducing Overfitting with Dropout | Part 3 | Adding Dropout Layers in PyTorch |
X55e411GmdQ |
| Jul. 2023 |
Scaling PyTorch Model Training - Sebastian Raschka at CVPR |
LCTysvIJGqY |
| Jul. 2023 |
Unit 4.3 | Training a Multilayer Perceptron in PyTorch | Part 2 |
3LzPXjobVdM |
| Jul. 2023 |
Unit 5.2 | Training a Multilayer Perceptron in PyTorch Lightning | Part 3 |
8NKXArrnJlQ |
| Jul. 2023 |
Unit 7.3 | Convolutional Neural Network Architectures | Part 3 | Key Architecture Ideas |
uptFqRFwuTA |
| Jul. 2023 |
Unit 1.6 | Perceptron in Python | Part 2| Coding Example |
IC7iT2gVni4 |
| Jul. 2023 |
Unit 6.1 | Model Checkpointing and Early Stopping | Part 2 |
FmzeUcC7bKc |
| Jul. 2023 |
Lightning Progress Bar |
z0sJ6uhITvY |
| Jul. 2023 |
Reduce Infrastructure Cost by Moving Beyond MLOps |
2q3FhiLjIYk |
| Jul. 2023 |
Unit 7.4 | Training CNNs | Part 2 | From MLP to CNN |
vMhfdudHIN0 |
| Jul. 2023 |
Unit 8.7 | A Large Language Model for Classification | Part 2 |
uGTQbCF36uo |
| Jul. 2023 |
Unit 4 | Training Multilayer Neural Networks |
vrAQPyHKFas |
| Jul. 2023 |
Unit 7.5 | Data Augmentation | Part 3 | Training a ResNet on Augmented Data |
eo_wJW6TYNU |
| Jul. 2023 |
Unit 8.1 | Working with Text Data | Part 2 | The Bag-of-Words Model |
obsQ9WCtFx4 |
| Jul. 2023 |
NVIDIA NeMo |
rFAX1-4DSr4 |
| Jul. 2023 |
Unit 7.2 | How Convolutional Networks Work | Part 1 |
T5ITvjXWhFE |
| Jul. 2023 |
Unit 3.6 | Training a Logistic Regression Model in PyTorch | Part 2 |
MMcOAT3KNgo |
| Jul. 2023 |
Unit 6 | Essential Deep Learning Tips & Tricks |
lTcNNFMXY5Q |
| Jul. 2023 |
Unit 3.3 | Model Training with Stochastic Gradient Descent | Part 3 |
xhp4RkecIH8 |
| Jul. 2023 |
Unit 4.5 | Multilayer Neural Networks for Regression | Part 1 | Architecture and Loss Function |
1WHy50Bt2wg |
| Jul. 2023 |
Unit 4.1 | Logistic Regression for Multiple Classes | Part 1 | The Softmax Regression Model |
cVbbJ2ZNrYw |
| Jul. 2023 |
Unit 5.8 | Adding Functionality with Callbacks |
-7WXeqRBzzQ |
| Jul. 2023 |
Unit 3.7 | Feature Normalization | Part 2 | Common Feature Normalization Techniques |
Mw7wJTHep9c |
| Jul. 2023 |
Unit 1.5 | Setting Up Our Computing Environment |
PQjzAhO__w4 |
| Jul. 2023 |
Unit 9.1 | Accelerated Model Training via Mixed-Precision Training | Part 2 | Hands-On Code Demo |
vvxJvSfh8Xg |
| Jul. 2023 |
Lightning DevCon Live Stream - internal employees only |
R4t8ERneNOM |
| Jul. 2023 |
Unit 3.7 | Feature Normalization | Part 1 | The Problem with Features on Different Scales |
eTP3sXLjV5I |
| Jul. 2023 |
Unit 3.1 | Using Logistic Regression for Classification | Part 3 | The Logistic Regression Loss |
Ciyp8aYBsHQ |
| Jul. 2023 |
Unit 5.6 | The Benefits of Logging | Part 3 | Coding |
8PBSliC9_AU |
| Jul. 2023 |
Unit 2.4 | Improving Code Efficiency with Linear Algebra | Part 3 | Multiplying Two Matrices |
yzsIRbvH804 |
| Jul. 2023 |
Unit 5.4 | Making Code Reproducible | Part 1 | Sources of Randomness |
m_s1g41Cj_M |
| Jul. 2023 |
Unit 4.1 | Logistic Regression for Multiple Classes | Part 3 | From Softmax Scores to Class Labels |
nTWS26lQP40 |
| Jul. 2023 |
Unit 1 | Welcome to Machine Learning and Deep Learning |
6Py-tIEiXKw |
| Jul. 2023 |
Unit 2.4 | Improving Code Efficiency with Linear Algebra | Part 4 | Unequal Tensor Shapes |
J0lLeaWSBWM |
| Jul. 2023 |
Unit 8.6 | Large Language Models | Part 2 | Generative Pretrained Transformer (GPT) |
F-9Ekl4v_YU |
| Jul. 2023 |
Unit 3.4 | Automatic Differentiation in PyTorch |
iNcxvqDEEj4 |
| Jul. 2023 |
Unit 2.2 | What are Tensors? | Part 2 | Tensors and Array Libraries |
2XtB7KPjskk |
| Jul. 2023 |
Unit 1.1 | What is Machine Learning? | Part 1 | How does it work? |
y36U3yvKT7A |
| Jul. 2023 |
Unit 6.1 | Model Checkpointing and Early Stopping | Part 3 |
FLqHaWgWuiM |
| Oct. 2023 |
Unit 2.2 | What are Tensors? | Part 01 | Tensors for Data |
cwcaTNHgGuM |
| Jan. 2024 |
Implementing Your AI Strategy with Lightning Studio | Luca Antiga presentation at AI Summit Dec 2023 |
5e1UezWwukA |
| Feb. 2024 |
AI Regulation: A Fireside Conversation about AI's relationship with Washington DC |
1C_mdeD9vE4 |
| Mar. 2024 |
Meet Studio Templates | Get started today for free with Studio Templates |
78aQx7QcryU |
| Mar. 2024 |
Meet Studio | Turn ideas into AI, Lightning Fast | from Lightning AI Creators of PyTorch Lightning |
wYV8rPKTbSc |
| Jul. 2024 |
The Thunder Sessions | Session 1 |
hOeAkbSwMCE |
| Jul. 2024 |
The Thunder Sessions | Session 2 |
8KLL3aCiiWg |
| Jul. 2024 |
The Thunder Sesssions | Session 3 | Deep Learning Compilers |
HtL-T1nw0Rw |
| Jul. 2024 |
The Thunder Sessions | Session 2 |
Od1STXifgjE |
| Jul. 2024 |
The Thunder Sessions | Session 4 | Transforms |
t9Fj5VjIpac |
| Aug. 2024 |
The Thunder Sessions | Session 5 | Speedups in Llama 3 |
0kuy63u1kZ8 |
| Aug. 2024 |
Meet LitServe - The fast, simple way to deploy AI models |
_0K3u5dmf9A |
| Aug. 2024 |
The Thunder Sessions | Session 6 | More Transforms, Less Theory |
i79Op6DXI7c |
| Sep. 2024 |
The Thunder Sessions | Session 7 | Fusing Kernels with Thunder & Triton |
DF7_XGUmCD8 |
| Sep. 2024 |
The Thunder Sessions | Session 8 |
-p9nlwhqh30 |
| Sep. 2024 |
The Thunder Sessions | Session 9 | Applying custom kernels and fusions to large models |
TCvLw_Do2lU |
| Oct. 2024 |
The Thunder Sessions | Session 10 | LLL: Liger-Kernel+LitGPT+Llama 3.2 |
3H_aw6o-d9c |
| Oct. 2024 |
Thunder Sessions | Session 11 |
0zSpp1ZpS34 |
| Oct. 2024 |
The Thunder Sessions | Session 12 |
EfNzQKQFcxk |