search

yangyangyang127 / APE

[ICCV 2023] Code for "Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement"
135 stars 12 forks source link

How do you calculate the FLOPs of the model #14

Open X-funbean opened 2 months ago

X-funbean commented 2 months ago

Hi! I'm interested in getting the training/inference FLOPs of the model. Could you provide the source code for calculating the training GFLOPs in Fig. 1? Many thanks! image

yangyangyang127 commented 2 months ago

hi. thanks for your attention. actually we present the flops in the backward propagation, i.e., calculation of the gradients, because only a small module needs to be optimized.

---- Replied Message ---- | From | @.> | | Date | 06/28/2024 21:24 | | To | @.> | | Cc | @.***> | | Subject | [yangyangyang127/APE] How do you calculate the FLOPs of the model (Issue #14) |

Hi! I'm interested in getting the training/inference FLOPs of the model. Could you provide the source code for calculating the training GFLOPs in Fig. 1? Many thanks! image.png (view on web)

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>