from __future__ import print_function, division from builtins import range # Note: you may need to update your version of future # sudo pip install -U future from keras.models import Model from keras.layers import Dense, Activation, Conv2D, MaxPooling2D, Flatten, Input import matplotlib.pyplot as plt import pandas as pd import numpy as np from util import getKaggleMNIST3D, getKaggleFashionMNIST3D, getCIFAR10 # get the data Xtrain, Ytrain, Xtest, Ytest = getKaggleFashionMNIST3D() # get shapes N, H, W, C = Xtrain.shape K = len(set(Ytrain)) # make the CNN i = Input(shape=(H, W, C)) x = Conv2D(filters=32, kernel_size=(3, 3))(i) x = Activation('relu')(x) x = MaxPooling2D()(x) x = Conv2D(filters=64, kernel_size=(3, 3))(x) x = Activation('relu')(x) x = MaxPooling2D()(x)
from builtins import range # Note: you may need to update your version of future # sudo pip install -U future from keras.models import Model from keras.layers import Dense, Activation, Conv2D, MaxPooling2D, Flatten, Input import matplotlib.pyplot as plt import pandas as pd import numpy as np from util import getKaggleMNIST3D, getKaggleFashionMNIST3D, getCIFAR10 # get the data Xtrain, Ytrain, Xtest, Ytest = getKaggleFashionMNIST3D() # get shapes N, H, W, C = Xtrain.shape K = len(set(Ytrain)) # make the CNN i = Input(shape=(H, W, C)) x = Conv2D(filters=32, kernel_size=(3, 3))(i) x = Activation('relu')(x) x = MaxPooling2D()(x) x = Conv2D(filters=64, kernel_size=(3, 3))(x)