imagenet1k

IMAGENET-1K resnet50-pytorch

Model Description

resnet50-pytorch trained on imagenet-1k dataset with advanced augmentation techniques.

Model Architecture

• Architecture: resnet50-pytorch
• Dataset: IMAGENET-1K
• Classes: 1000

Training Configuration

• Batch Size: 256
• Optimizer: sgd (momentum=0.9, weight_decay=1e-3)
• Scheduler: cosine
• Augmentation: HorizontalFlip, ShiftScaleRotate, Cutout, ColorJitter
• MixUp: Alpha=0.2
• Label Smoothing: 0.1
• Mixed Precision: True
• Gradient Clipping: 1.0

Performance

• Best Test Accuracy: 73.84%
• Total Epochs Trained: 92
• Final Train Accuracy: 42.78%
• Final Test Accuracy: 52.61%

Training History

• Best Epoch: 90
• Train Loss: 6.1800 → 3.6653
• Test Loss: 5.1372 → 2.1657

Usage

import torch
from huggingface_hub import hf_hub_download

# Download model
checkpoint_path = hf_hub_download(
    repo_id="pandurangpatil/imagenet1k",
    filename="best_model.pth"
)

# Load checkpoint
checkpoint = torch.load(checkpoint_path, map_location='cpu', weights_only=False)

# Load model (you'll need to have the model definition)
# from models import get_model
# model = get_model('resnet50-pytorch', num_classes=1000)
# model.load_state_dict(checkpoint['model_state_dict'])
# model.eval()

Training Details

• Dataset: IMAGENET-1K (Unknown train, Unknown test)
• Classes: 1000
• Image Size: Unknown
• Normalization: mean=Dataset-specific, std=Dataset-specific

Files

• best_model.pth - Best performing model checkpoint
• training_curves.png - Training/test accuracy and loss curves
• lr_finder_plot.png - Learning rate finder results
• metrics.json - Complete training history
• config.json - Hyperparameter configuration

License

MIT

Citation

@misc{resnet50-pytorch-imagenet-1k,
  title = {IMAGENET-1K resnet50-pytorch},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/pandurangpatil/imagenet1k}
}