license: apache-2.0 language: - en base_model: - bobbysam/resnet18-image-detector library_name: transformers pipeline_tag: image-classification tags: - computer-vision - image-classification - ai-detection - pytorch - resnet datasets: - custom metrics: - accuracy - precision - recall - f1 model-index: - name: resnet18-image-detector results: - task: type: image-classification name: AI vs Real Image Detection dataset: name: Custom AI Detection Dataset type: custom metrics: - type: accuracy value: 0.95 name: Accuracy - type: f1 value: 0.94 name: F1 Score - type: precision value: 0.93 name: Precision - type: recall value: 0.96 name: Recall

ResNet18 AI Image Detector

Repository: bobbysam/resnet18-image-detector

🧠 What does this model do?

This is a ResNet18-based deep neural network trained to detect whether an input image is a real photograph or AI-generated (binary classification: real vs. ai_generated).
It is part of the ProofGuard project and can be used to build trustworthy AI image detection pipelines.

Key Features:

🔬 Binary classification: Real vs AI-generated images
🚀 Fast inference with ResNet18 architecture
🤗 Compatible with Hugging Face Transformers
📊 Comprehensive evaluation metrics
🎯 Easy-to-use inference API

resnet18-image-detector

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2759
Accuracy: 0.9555
F1: 0.9555
Precision: 0.9560
Recall: 0.9555

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.3995	0.0533	50	0.6382	0.6905	0.6824	0.7146	0.6905
1.1186	0.1067	100	0.4529	0.8619	0.8619	0.8634	0.8619
0.7891	0.16	150	0.3469	0.9124	0.9124	0.9124	0.9124
0.7927	0.2133	200	0.3208	0.9305	0.9305	0.9305	0.9305
0.7672	0.2667	250	0.3095	0.9417	0.9418	0.9418	0.9417
0.7395	0.32	300	0.3625	0.9001	0.8992	0.9125	0.9001
0.6937	0.3733	350	0.2940	0.9483	0.9483	0.9483	0.9483
0.6654	0.4267	400	0.3315	0.9268	0.9266	0.9329	0.9268
0.6647	0.48	450	0.2872	0.9487	0.9487	0.9497	0.9487
0.7021	0.5333	500	0.2857	0.9488	0.9488	0.9491	0.9488
0.6458	0.5867	550	0.2759	0.9555	0.9555	0.9560	0.9555
0.6634	0.64	600	0.2830	0.9516	0.9515	0.9517	0.9516
0.6534	0.6933	650	0.2858	0.9507	0.9506	0.9533	0.9507

Framework versions

Transformers 4.54.1
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.21.4