def predict(input_path):
(X_test, y_test)= mcz_input.read_data(input_path)
X_test = X_test.astype('float32')
X_test /= 255
nb_classes = 5
Y_test = np_utils.to_categorical(y_test, nb_classes)
model = load_model('model.h5')
res = model.predict(X_test)
acts = [np.argmax(i) for i in res]
exps = [np.argmax(i) for i in Y_test]
cnt = 0.0
total = 0.0
for (a,e) in zip(acts, exps):
if a == e:
cnt += 1.0
total += 1.0
print(input_path, cnt/total)
from __future__ import print_function
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras.models import load_model
import mcz_input
import sys
import numpy as np
(X_test, y_test)= mcz_input.read_data('../deeplearning/predict.txt')
X_test = X_test.astype('float32')
X_test /= 255
nb_classes = 5
Y_test = np_utils.to_categorical(y_test, nb_classes)
print(Y_test)
model = load_model('model.h5')
res = model.predict(X_test)
print([np.argmax(i) for i in res])
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras.layers.normalization import BatchNormalization
import mcz_input
import sys
batch_size = 32
nb_classes = 5
nb_epoch = 200
data_augmentation = True
img_rows, img_cols = 112, 112
img_channels = 3
(X_train, y_train)= mcz_input.read_data('../deeplearning/train.txt')
(X_test, y_test)= mcz_input.read_data('../deeplearning/test.txt')
print('X_train shape:', X_train.shape, X_train[0][0][0][0])
print('y_train shape:', y_train.shape, y_train[0][0])
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same', input_shape=X_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
import coremltools
import sys
sys.path.append('../keras/')
import mcz_input
(X_test, y_test)= mcz_input.read_data('../deeplearning/predict.txt')
#(X_test, y_test)= mcz_input.read_data('../deeplearning/train.txt')
X_test = X_test.astype('float32')
X_test /= 255
#print(X_test)
#print(y_test)
print('loading..')
model = coremltools.models.MLModel('Momomind.mlmodel')
print('predicting..')
res = model.predict(X_test)
print(res)