Caffe2 is an open-source deep learning framework. It's focus is on efficiency and works with constrained environments such as on mobile devices.
- Blobs and operations
- Operators and Net
- Simple Linear Regression (on one feature of Boston Dataset)
- Classification using Caffe2
- Image pre-processing pipeline
- Prediction using pretrained models
Install Caffe2 with Python bindings.
To download a model locally, run
python -m caffe2.python.models.download squeezenet
which will create a folder squeezenet/ containing both an init_net.pb and predict_net.pb.
To install a model, run
python -m caffe2.python.models.download -i squeezenet
which will allow later imports of the model directly in Python:
from caffe2.python.models import squeezenet
print(squeezenet.init_net.name)
print(squeezenet.predict_net.name)
`