DeepFashion2 icon indicating copy to clipboard operation
DeepFashion2 copied to clipboard

Published 20 hours ago • verified publisher icon switchablenorms

How to train with entire dataset? Anyone mind sharing their trained model?

Open lolitsgab opened this issue 5 years ago • 2 comments

Running on Google Colab and training using Mask-RCNN. I converted the dataset into the COCO format using the given script, but it seem's that it can only load about 32k images into Mask RCNN before I run out of memory (I mainly suspect pycoco's loadAnns()).

I've been training with 32k images at a time (complete training with 32k images, retrain with 32k images part 2, retrain with other 32k images... etc). So far I've only done the first three 32k image batches, and it is obviously very time consuming as I have to keep retraining. Is there a way to circumvent this? Anyone mind sharing their trained model?

lolitsgab avatar Nov 04 '19 03:11 lolitsgab

i have trained 191961 train images and 32153 validation images but accuracy not good (39 epoch)

Manishsinghrajput98 avatar Feb 11 '20 11:02 Manishsinghrajput98

https://manishsinghrajput96.blogspot.com/ step by step implementation

Manishsinghrajput98 avatar Jul 09 '20 17:07 Manishsinghrajput98