Visual scenes are often comprised of sets of independent objects. Yet, current vision models make no assumptions about the nature of the pictures they look at.

Yannic Kilcher explore a paper on object-centric learning.

By imposing an objectness prior, this paper a module that is able to recognize permutation-invariant sets of objects from pixels in both supervised and unsupervised settings. It does so by introducing a slot attention module that combines an attention mechanism with dynamic routing.

Content index:

  • 0:00 – Intro & Overview
  • 1:40 – Problem Formulation
  • 4:30 – Slot Attention Architecture
  • 13:30 – Slot Attention Algorithm
  • 21:30 – Iterative Routing Visualization
  • 29:15 – Experiments
  • 36:20 – Inference Time Flexibility
  • 38:35 – Broader Impact Statement
  • 42:05 – Conclusion & Comments

deeplizard shows us how to add batch normalization to a convolutional neural network.

Content index:

  • 00:00 Welcome to DEEPLIZARD – Go to deeplizard.com for learning resources
  • 00:30 What is Batch Norm?
  • 04:04 Creating Two CNNs Using nn.Sequential
  • 09:42 Preparing the Training Set
  • 10:45 Injecting Networks Into Our Testing Framework
  • 14:55 Running the Tests – BatchNorm vs. NoBatchNorm
  • 16:30 Dealing with Error Caused by TensorBoard
  • 19:49 Collective Intelligence and the DEEPLIZARD HIVEMIND

deeplizard teaches us how to set up debugging for PyTorch source code in Visual Studio Code.

Content index:

  • 00:00 Welcome to DEEPLIZARD – Go to deeplizard.com for learning resources
  • 00:27 Visual Studio Code
  • 00:55 Python Debugging Extension
  • 01:30 Debugging a Python Program
  • 03:46 Manual Navigation and Control of a Program
  • 06:34 Configuring VS Code to Debug PyTorch
  • 08:44 Stepping into PyTorch Source Code
  • 10:36 Choosing the Python Environment00:00 Welcome to DEEPLIZARD – Go to deeplizard.com for learning resources
  • 00:27 Visual Studio Code
  • 00:55 Python Debugging Extension
  • 01:30 Debugging a Python Program
  • 03:46 Manual Navigation and Control of a Program
  • 06:34 Configuring VS Code to Debug PyTorch
  • 08:44 Stepping into PyTorch Source Code
  • 10:36 Choosing the Python Environment
  • 12:30 Collective Intelligence and the DEEPLIZARD HIVEMIND

deeplizard debugs the PyTorch DataLoader to see how data is pulled from a PyTorch data set and is normalized.

We see the impact of several of the constructor parameters and see how the batch is built.

Content index:

  • 0:00 Welcome to DEEPLIZARD – Go to deeplizard.com
  • 0:45 Overview of Program Code
  • 3:12 How to Use Zen Mode
  • 3:56 Start the Debugging Process
  • 4:38 Initializing the Sampler Based on the Shuffle Parameter
  • 5:35 Debugging next(iter(dataloader))
  • 7:57 Building the Batch Using the Batch Size
  • 10:37 Get the Elements from Dataset
  • 18:43 Tensor to PIL Image
  • 20:41 Thanks for Contributing to Collective Intelligence

deeplizard teaches us how to normalize a dataset. We’ll see how dataset normalization is carried out in code, and we’ll see how normalization affects the neural network training process.

Content index:

  • 0:00 Video Intro
  • 0:52 Feature Scaling
  • 2:19 Normalization Example
  • 5:26 What Is Standardization
  • 8:13 Normalizing Color Channels
  • 9:25 Code: Normalize a Dataset
  • 19:40 Training With Normalized Data