CNN Class

brew is Caffe2’s new API for building models. The CNNModelHelper filled this role in the past, but since Caffe2 has expanded well beyond excelling at CNNs it made sense to provide a ModelHelper object that is more generic. You may notice that the new ModelHelper has much the same functionality as CNNModelHelper. brew wraps the new ModelHelper making building models even easier than before.

CNNModelHelper is being deprecated. Refer to brew and python/model_helper.py for its replacements.

CNNModelHelper

Code: cnn.py | API Docs: cnn.CNNModelHelper

CNNModelHelper is a helper class so you can write CNN models more easily, without having to manually define parameter initializations and operators separately. You will find many built-in helper functions as well as automatic support for a collection of operators that are listed below.

Example Usage

1
2
3
4
5
6
7
8
9
10
11
12
13
14

# Create the input data
data = np.random.rand(16, 100).astype(np.float32)

# Create labels for the data as integers [0, 9].
label = (np.random.rand(16) * 10).astype(np.int32)

workspace.FeedBlob("data", data)
workspace.FeedBlob("label", label)

# Create model using a model helper
m = cnn.CNNModelHelper(name="my first net")
fc_1 = m.FC("data", "fc1", dim_in=100, dim_out=10)
pred = m.Sigmoid(fc_1, "pred")
[softmax, loss] = m.SoftmaxWithLoss([pred, "label"], ["softmax", "loss"])

Edit on GitHub