1 # How to configure Caffe launcher
3 For enabling Caffe launcher you need to add `framework: caffe` in launchers section of your configuration file and provide following parameters:
5 * `device` - specifies which device will be used for infer (`cpu`, `gpu_0` and so on).
6 * `model` - path to prototxt file with Caffe model for your topology.
7 * `weights` - path to caffemodel file with weights for your topology.
8 * `adapter` - approach how raw output will be converted to representation of dataset problem, some adapters can be specific to framework. You can find detailed instruction how to use adapters [here][adapters].
10 You also can specify batch size for your model using `batch` and allow to reshape input layer to data shape, using specific parameter: `allow_reshape_input` (default value is False).
12 Caffe launcher config example:
18 model: path_to_model/alexnet.prototxt
19 weights: path_to_weights/alexnet.caffemodel
20 adapter: classification
24 [adapters]: ./tools/accuracy_checker/accuracy_checker/adapters/README.md