Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -51,11 +51,11 @@ The code can be easily adapted to other models, if you will to utilize CLIP-COUN

###### Evaluation

Our evaluation is based both on CLIP-COUNT and YOLO.
Our evaluation is based both on CLIP-COUNT and YOLOS.

For CLIP-COUNT setup, refer to previous section.

For YOLO setup, please refer to [YOLOv9 docs](https://docs.ultralytics.com/models/yolov9/).
For YOLOS setup, please refer to the [Hugging Face docs](https://huggingface.co/docs/transformers/en/model_doc/yolos).

## Run and Evaluate:
<p align="center">
Expand Down
7 changes: 6 additions & 1 deletion clip_count/models/clip_count_model.py
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,12 @@
import einops
import functools
import operator
class CLIPCount(nn.Module):

from huggingface_hub import PyTorchModelHubMixin


class CLIPCount(nn.Module, PyTorchModelHubMixin,
repo_url="https://github.com/songrise/CLIP-Count/tree/main", pipeline_tag="zero-shot-image-classification", license="mit"):
def __init__(self, fim_depth:int=4,
fim_num_heads:int=8,
mlp_ratio:float=4.,
Expand Down