Downloads · 30 days
0
resnett50-imagenet
Sijuade/resnett50-imagenet
resnett50-imagenet is a machine learning model from Sijuade. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Place your trained model checkpoints here.
Access
Public
Updated Oct 24, 2025
Repo size
615 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.ckpt410 MB · 100%
At a glance
- Access
- Public
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025
- SHA
- a912d126
Model card
From the Hugging Face model README
Models Directory
Place your trained model checkpoints here.
Usage
Copy from Training Directory
# Copy a trained checkpoint
cp /home/ubuntu/imagenet/checkpoints/resnet50-epoch=89-val_acc1=0.7500.ckpt .
# Or copy the latest checkpoint
cp /home/ubuntu/imagenet/checkpoints/last.ckpt .
Use in Docker
When running the Streamlit app in Docker, reference the checkpoint as:
/app/models/resnet50-epoch=89-val_acc1=0.7500.ckpt
The models/ directory is mounted as a volume in Docker, so you can:
- Add/update checkpoints without rebuilding the container
- Access them from the Streamlit UI
Supported Formats
- PyTorch Lightning checkpoints (.ckpt)
- Standard PyTorch checkpoints (.pth, .pt)
Example
# List available checkpoints
ls -lh
# Test inference with a checkpoint
cd ..
python inference.py \
--image test_image.jpg \
--checkpoint models/resnet50-epoch=89.ckpt \
--verbose
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025