I have perform an image duplication detection with pytorch pretrained model. I am using resnet152 for extracing embedding vector. I already embedding millions of record already. And resnet152 is too big which consume 16GB of GPU memory. I want to switch to resnet50 which use only 4GB of GPU memeory. The problem for me is they are not generate the same embedding output. Any suggestion that I can approach this better?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Using ResNet50 weights inside `CLIPModel` | 0 | 750 | June 23, 2021 | |
Weight duplication/reuse for small model config changes? | 0 | 290 | May 10, 2022 | |
Not a language model - remove word embedding weights from model for lighter cuda util | 1 | 627 | October 6, 2022 | |
ViT Model increasing CPU RAM when moving to GPU | 0 | 228 | August 12, 2022 | |
Saving Manually Resized Embeddings for a Pretrained Bert Model (I believe I am asking this correctly) | 0 | 115 | November 7, 2024 |