Downloads · 30 days
6
5% of all-time downloads
DePerceiver
Max-Ploter/DePerceiver
DePerceiver is a object detection model from Max-Ploter. Use it when you need objects located in an image. The card lists the license as apache-2.0.
<img src="https://raw.githubusercontent.com/maxploter/DePerceiver/refs/heads/main/deperceiverr50/deperceiver.png" alt="DePerceiver R50 Image"/
All-time downloads
124
Public
Repo size
171 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin171 MB · 100%
At a glance
- Task
- Object Detection
- License
- apache-2.0
- Access
- Public
- Created
- Mar 9, 2025
- Updated
- Mar 10, 2025
- SHA
- 987d1657
Model card
From the Hugging Face model README
Detection Perceiver Model
<img src="https://raw.githubusercontent.com/maxploter/DePerceiver/refs/heads/main/de_perceiver_r50/de_perceiver.png" alt="DePerceiver R50 Image"/>Usage
from huggingface_hub import snapshot_download
import torch
import json
import sys
# Download model
repo_path = snapshot_download(repo_id="Max-Ploter/DePerceiver")
# Add to Python path to access modeling_detection_perceiver.py
sys.path.append(repo_path)
from modeling_detection_perceiver import build_model
# Load config
with open(f"{repo_path}/config.json") as f:
config = json.load(f)
# Build and load model
model = build_model(config)
model.load_state_dict(torch.load(f"{repo_path}/detection_perceiver_model_weights_pytorch.bin"))
Dependencies
pip install torch torchvision perceiver-pytorch
- Task
- Object Detection
- License
- apache-2.0
- Created
- Mar 9, 2025
- Updated
- Mar 10, 2025