search

A-new-b / flex_edit

we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing.
24 stars 0 forks source link

Train Cost #2

Open mo230761 opened 2 months ago

mo230761 commented 2 months ago

I really appreciate your work. Can a 32GB V100 be used for training? Thanks！

Lum1104 commented 2 months ago

https://arxiv.org/pdf/2408.12429

You can get the training details from our ongoing paper (Appendix A Implementation Details). We trained the model at A100 (40G) with batch size=4. You can tried with different batch size or other techniques for the training. Stay tuned we would upload the code.

mo230761 commented 2 months ago

OK!Thank you!

bxhsort commented 1 month ago

https://arxiv.org/pdf/2408.12429

You can get the training details from our ongoing paper (Appendix A Implementation Details). We trained the model at A100 (40G) with batch size=4. You can tried with different batch size or other techniques for the training. Stay tuned we would upload the code.

Presumably what emits the code