Resource of free step by step video how to guides to get you started with machine learning.
Tuesday, April 30, 2024
Mini Batches in Graph Neural Network
In this pytorch tutorial, we looked into performing mini-batch training in graph convolutional networks (GCN). We also saw how to use ClusterData and ClusterLoader from pytorch geometric to do mini-batch training in graph neural networks (GNN). ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 🔗 jupyter notebook I built in this video: https://github.com/mashaan14/YouTube-channel/blob/main/notebooks/2024_04_29_GNN_mini_batch.ipynb ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ https://www.youtube.com/playlist?list=PL8Q742wf_oLXBo9hk3NepUMmnIvfYEJy2 ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ - my website ➡️ https://mashaan14.github.io/mashaan/ - my github ➡️ https://github.com/mashaan14 - my linkedin ➡️ https://linkedin.com/in/mashaan ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 📹 Video edit: Adobe Premiere Rush 🎧 Audio enhancement: Adobe Podcast ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ Chapters: 00:00 start 00:11 what is a mini-batch? 02:26 why do we need a mini-batch? 05:07 what is a good size for a mini-batch? 06:15 why is it difficult to do a mini-batch in GNN? 09:42 introducing Cluster-GCN 11:31 diagonal block adjacency 12:33 going back to Cluster-GCN 16:48 introducing Metis 18:10 why not spectral clustering? 18:51 start of the code 19:09 install pytorch-geometric dependencies 20:58 full-batch training 21:35 mini-batch training 24:22 why the fast convergance with mini-batch? ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ #GNN #GCN #pytorchgeometric #GNNs #Cluster-GCN #graphneuralnetwork #ai #deeplearning #machinelearning #python #neuralnetworks #artificialintelligence #pytorch #imageclassification #GPU #TPU #tutorial
Labels:
ArtificialIntelligence,
deeplearning,
huggingface,
machinelearning,
matplotlib,
programming,
scikitlearn,
TensorFlow,
transformers,
visiontransformers
Published by Free artificial intelligence and machine learning video tutorial resource
Related video tutorials
Subscribe to:
Post Comments (Atom)
Most watched
-
Quick answer: Qwen 3 32B needs about 22.7 GB of VRAM at Q4_K_M with a 4k-token context — a used 24 GB card like the RTX 3090 is the minimu...
-
Using GPUs in TensorFlow, TensorBoard in notebooks, finding new datasets, & more! (#AskTensorFlow) [Collection] In a special live ep...
-
Inside TensorFlow: Summaries and TensorBoard [Collection] Take an inside look into the TensorFlow team’s own internal training sessions-...
-
Quick answer: DeepSeek V4 Flash is a Mixture-of-Experts model: all 284 billion parameters must be stored, so combined RAM plus VRAM — not ...
-
Quick answer: For an 8B model at Q4, local electricity costs roughly $0.05 per million output tokens — against about $0.53 per million ble...
-
Hey everyone This is Ujjwal kapil B.tech 2nd year Ai and Ml In this video we covered one of the most important question "COLLEGE KAB O...
-
Quick answer: For machine-learning work, buy an external SSD over a spinning hard drive, pick USB 3.2 Gen 2 (10 Gbps) or faster, and size f...
-
Quick answer: Yes, for most budget builders: a used RTX 3090 is still the cheapest route to 24 GB of VRAM with full CUDA support. Capacity...
-
This video is a crash course on understanding how finetuning on LLM models can be performed uing QLORA,LORA, Quantization using LLama2, Grad...
-
In this video, you'll learn how to use machine learning, computer vision and deep learning to create a football analysis system. This pr...
No comments:
Post a Comment