Where is pretrained ResNet101 in Keras and how obtain raw feature?

Question

I need pretrained ResNet101 in Keras but Python gives me error. In the documentation they write

keras.applications.resnet.ResNet101(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)

(https://keras.io/applications/) but when I import ResNet101 Python gives the error

AttributeError: module 'keras.applications' has no attribute 'resnet'

Moreover, I need the features calculated before the "pooling" layer, for example using VGG16 I'd do this:

myModel = Model(baseModel.input, baseModel.layers[-2].output)

How can I obtain them using ResNet? Thanks

score 1 · Accepted Answer · answered Jul 06 '19 at 20:57

The error is in your Keras version:

Feature Extraction

Last two layers of ResNet-101 are global average pooling and fully-connected layers. Because of that:

myModel.layers[-1].output # output of the FC layer
myModel.layers[-2].output # output of the global average pooling layer

score 0 · Answer 2 · answered Jul 23 '20 at 05:44

0

Try this one

keras.applications.ResNet101(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)

answered Jul 23 '20 at 05:44

sowmyakavali

Hello and welcome to Stack overflow. Don't just post code, but maybe try to explain in a few words why you think your answer solves the problem. – Ente Jul 23 '20 at 06:44

2 Answers2