Downloads · 30 days
1
0% of all-time downloads
detr-group37-resnet-101-dc5
slliac/detr-group37-resnet-101-dc5
detr-group37-resnet-101-dc5 is a machine learning model from slliac. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a fine-tuned version of [facebook/detr-resnet-101-dc5] for detecting vehicles in traffic camera images. The model was trained for improved vehicle detection in traffic scenarios.
All-time downloads
823
Public
Parameters
60.7M
728 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors486 MB · 100%
At a glance
- Model type
- detr
- Access
- Public
- Created
- Mar 12, 2025
- Updated
- Mar 26, 2025
- SHA
- f6a6ee39
Model card
From the Hugging Face model README
DETR for Traffic Analysis - detr-group37-resnet-101-dc5
## Model Description
This model is a fine-tuned version of [facebook/detr-resnet-101-dc5] for detecting vehicles in traffic camera images. The model was trained for improved vehicle detection in traffic scenarios.
## Training Data
The model was trained on the [slliac/isom5240-td-traffic-analysis], which contains traffic camera images with annotations for various vehicle types.
## Training Details
- **Base Model**: facebook/detr-resnet-101-dc5
- **Training Dataset Size**: 786 examples
- **Epochs**: 2
- **Batch Size**: 2
- **Learning Rate**: 5e-05
- **Weight Decay**: 1e-4
- **Training Date**: 2025-03-26
- **Final Training Loss**: 1.0996
- **Training Time**: 426.22 seconds
## Performance Metrics
- **Training Loss**: 1.0996
- **Samples per Second**: 3.69
- **Steps per Second**: 1.84
- Type
- detr
- Created
- Mar 12, 2025
- Updated
- Mar 26, 2025