dmlc/gluon-cv

Add Tutorial: Finetuning an existing SSD model

Open

#216 ouverte le 20 juil. 2018

Voir sur GitHub
 (3 commentaires) (0 réactions) (0 assignés)Python (1 224 forks)batch import
enhancementgood first issue

Métriques du dépôt

Stars
 (5 610 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

Hello! First of all, great work on this awesome lib!

I'm training my own SSDs for object detection, and I noticed there are no tutorials in the docs for fine-tuning a model in the zoo with a different dataset. I think it would be great for newcomers to have a starting point for quick training and results.

There is code for a ToySSD in the Object Detection sector of The Straight Dope, but you can't simply substitute the net in the Notebook for a net from the model_zoo.

Guide contributeur