GitHub / adrinorosario / scratch-or-finetune-on-small-datasets
A comparative study of the benefits of transfer learning over building a custom CNN architecture for a very small dataset.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adrinorosario%2Fscratch-or-finetune-on-small-datasets
PURL: pkg:github/adrinorosario/scratch-or-finetune-on-small-datasets
Stars: 0
Forks: 0
Open issues: 0
License: mit
Language: Jupyter Notebook
Size: 53.8 MB
Dependencies parsed at: Pending
Created at: 4 months ago
Updated at: 4 months ago
Pushed at: 4 months ago
Last synced at: 4 months ago
Topics: classification, cnn, cnn-classification, cnn-model, computer-vision, computervision, custommodels, flower-classification, oxford-flower-dataset, oxford102, pytorch-cnn, pytorch-implementation, research-paper, research-project, small-basic, transfer-learning