Downloads · 30 days
0
resnet18-intel-classifier
tialdrine/resnet18-intel-classifier
resnet18-intel-classifier is a image classification model from tialdrine. Use it when you need a label for an image. The card lists the license as mit.
📌 A ResNet18-based image classification model trained on the Intel Image Classification dataset, capable of recognizing six types of natural scenes. The model was fine-tuned using PyTorch, optimized for reproducibili…
Access
Public
Updated May 28, 2025
Repo size
89.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin44.8 MB · 100%
At a glance
- Task
- Image Classification
- License
- mit
- Access
- Public
- Created
- May 28, 2025
- Updated
- May 28, 2025
- SHA
- d221b947
Model card
From the Hugging Face model README
🏞️ ResNet18 Intel Image Classifier
📌 A ResNet18-based image classification model trained on the Intel Image Classification dataset, capable of recognizing six types of natural scenes. The model was fine-tuned using PyTorch, optimized for reproducibility and deployment in educational and practical scenarios.
🏷️ Classes
- Buildings
- Forest
- Glacier
- Mountain
- Sea
- Street
🧰 Training Procedure
- Loaded a pretrained ResNet18 model from
torchvision.models. - Replaced the final classification layer with a 6-unit fully connected layer.
- Resized all input images to 224x224 and applied ImageNet normalization.
- Used
ImageFolderandrandom_split()to divide the dataset:- 70% Training
- 15% Validation
- 15% Testing
- Training setup:
- Optimizer: Adam
- Loss Function: CrossEntropyLoss
- Batch size: 32
- Learning rate: 0.001
- Epochs: 5
- Saved the final model as
pytorch_model.bin.
📊 Performance
| Metric | Value |
|---|---|
| Final Train Accuracy | 90.08% |
| Final Val Accuracy | 88.74% |
⚙️ Framework & Environment
- Python: 3.10.12
- PyTorch: 2.0.1+cu118
- Torchvision: 0.15.2+cu118
- Platform: Google Colab (GPU enabled, CUDA support)
🧪 Hyperparameters
| Parameter | Value |
|---|---|
| Epochs | 5 |
| Batch Size | 32 |
| Optimizer | Adam |
| Learning Rate | 0.001 |
| Loss Function | CrossEntropy |
| Image Size | 224x224 |
| Data Split | 70% Train / 15% Val / 15% Test |
- Task
- Image Classification
- License
- mit
- Languages
- en
- Created
- May 28, 2025
- Updated
- May 28, 2025