306ff550f0ad54c01f922963be16ef96a0e1bbda,donkey/predictors/keras.py,ConvolutionPredictor,create,#ConvolutionPredictor#Any#,25

Before Change


        self.model_path = os.path.join(settings.MODELS_DIR, model_name)
        
        model = Sequential()
        model.add(Convolution1D(32, 3, input_shape=(128, 128)))
        model.add(Activation("relu"))
        model.add(MaxPooling1D(2))

        model.add(Convolution1D(32, 3))

After Change


        self.model_path = os.path.join(settings.MODELS_DIR, model_name)
        
        model = Sequential()
        model.add(Convolution2D(8, 3, 3, input_shape=(3, 120, 160)))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Convolution2D(12, 3, 3))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Convolution2D(16, 3, 3))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Convolution2D(32, 3, 3))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 8

Instances


Project Name: autorope/donkeycar
Commit Name: 306ff550f0ad54c01f922963be16ef96a0e1bbda
Time: 2016-12-23
Author: wroscoe@gmail.com
File Name: donkey/predictors/keras.py
Class Name: ConvolutionPredictor
Method Name: create


Project Name: autorope/donkeycar
Commit Name: 306ff550f0ad54c01f922963be16ef96a0e1bbda
Time: 2016-12-23
Author: wroscoe@gmail.com
File Name: donkey/predictors/keras.py
Class Name: ConvolutionPredictor
Method Name: create


Project Name: oarriaga/face_classification
Commit Name: e90157e7f01c85e9ef22f9679f1a40bda0efb51f
Time: 2017-06-30
Author: arriaga.camargo@gmail.com
File Name: src/models/cnn.py
Class Name:
Method Name: simpler_CNN


Project Name: oarriaga/face_classification
Commit Name: 70634a8da1f6d7cff5f33cd59b66c71a0a663251
Time: 2017-05-03
Author: arriaga.camargo@gmail.com
File Name: gender/models.py
Class Name:
Method Name: attention_CNN