SamsungSAILMontreal/ghn3
Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]
This project helps machine learning researchers and engineers accelerate the development of computer vision models. It provides pre-trained models that can generate initial parameters for various ImageNet-based neural network architectures. By starting with these predicted parameters, you can significantly reduce the time and computational resources needed to train new image classification models from scratch.
No commits in the last 6 months.
Use this if you are a machine learning practitioner working with computer vision models and want to quickly initialize and fine-tune deep neural networks for image classification tasks, especially those based on ImageNet.
Not ideal if you are a non-technical user or if your primary goal is to deploy pre-built, production-ready image classification applications without any model training or fine-tuning.
Stars
39
Forks
8
Language
Shell
License
MIT
Category
Last pushed
Aug 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SamsungSAILMontreal/ghn3"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SamsungSAILMontreal/nino
Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]
graphdeeplearning/graphtransformer
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to...
vijaydwivedi75/gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional...
snap-stanford/relgt
Relational Graph Transformer
omron-sinicx/crystalframer
The official code respository for "Rethinking the role of frames for SE(3)-invariant crystal...