在 MNIST 数据集上训练后，如何在 keras 中使用 cnn 预测我自己的图像

Question

I have made a convolutional neural.network to predict handwritten digits using MNIST dataset but now I am stuck at predicting my own image as input to cnn,I have saved weights after training cnn and want to use that to predict my own image (NOTE: care is taken that my input image is 28x28)

code:

new_mnist.py:

ap = argparse.ArgumentParser()
ap.add_argument("-s", "--save-model", type=int, default=-1,
help="(optional) whether or not model should be saved to disk")  
ap.add_argument("-l", "--load-model", type=int, default=-1,
help="(optional) whether or not pre-trained model should be loaded")
ap.add_argument("-w", "--weights", type=str,
help="(optional) path to weights file")
args  = vars(ap.parse_args())

# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)

# load data
print("[INFO] downloading data...")
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).astype('float32')
print(X_test.shape[0])

# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255
# one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]

# build the model
print("[INFO] compiling model...")
model = LeNet.build(num_classes = num_classes,weightsPath = args["weights"]          if args["load_model"] > 0 else None)
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

if args["load_model"] < 0:
# Fit the model
print("[INFO] training...")
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=1,    batch_size=200, verbose=2)
# Final evaluation of the model
print("[INFO] evaluating...")
scores = model.evaluate(X_test, y_test, verbose=0)
print("Baseline Error: %.2f%%" % (100-scores[1]*100))
elif args["load_model"] > 0:
im = imread("C:\\Users\\Divyesh\\Desktop\\mnist.png")
im = im/255
pr = model.predict_classes(im)
print(pr)

# check to see if the model should be saved to file
if args["save_model"] > 0:
print("[INFO] dumping weights to file...")
model.save_weights(args["weights"], overwrite=True)

l.net.py:

class LeNet:
@staticmethod
def build(num_classes,weightsPath = None):
# create model
    model = Sequential()
    model.add(Convolution2D(30, 5, 5, border_mode='valid', input_shape=(1, 28, 28), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Convolution2D(15, 3, 3, activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(num_classes, activation='softmax'))
    # Compile model
    #model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    if weightsPath is not None:
        model.load_weights(weightsPath)
    return model

in new_mnist.py I have called predict(im) in which im is 28x28 image but after running this program I get error as:

ValueError: Error when checking : expected conv2d_1_input to have 4      dimensions, but got array with shape (28, 28)

HELP!!!

Answer 1

Try:

pr = model.predict_classes(im.reshape((1, 1, 28, 28)))

Here : first dimension comes from examples (you need to specify it even if you have only one example), second comes from channels (as it seems that you use Theano backend) and rest are spatial dimensions.

Answer 2

It should be noted that the images must be uploaded in grayscale.

1. Like:

im = im[:,:,0]

2. Or

import cv2

im = cv2.imread('C:\\Users\\Divyesh\\Desktop\\mnist.png', cv2.IMREAD_GRAYSCALE)