jupyter上运行结果如下
(x_train,y_train), (x_test,y_test) = mnist.load_data()
x_train = x_train.reshape(x_train.shape[0],28,28,1).astype('float32')
x_test = x_test.reshape(x_test.shape[0],28,28,1).astype('float32')
x_train /= 255
x_test /= 255
y_train = np_utils.to_categorical(y_train,10)
y_test = np_utils.to_categorical(y_test,10)
model = Sequential()
model.add(Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu', input_shape = (28,28,1)))
model.add(MaxPooling2D(pool_size = (2,2)))
model.add(Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu'))
model.add(MaxPooling2D(pool_size = (2,2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(128, activation = 'relu'))
model.add(Dense(10,activation = 'softmax'))
model.compile(loss = 'categorical_crossentropy', optimizer = Adadelta(), metrics = ['accuracy'])
model.fit(x_train,y_train,batch_size=100,epochs=20)
# 将图片转为灰度图并调整为28*28大小
def convert_gray(f, **args):
rgb=io.imread(f)
gray=color.rgb2gray(rgb)
dst=transform.resize(gray,(28,28))
return dst
test_gray_resize = convert_gray('number3.png')
运行结果如上,我手写的数字3,预测结果是6,后面不管我用哪个自己手写的图片验证,预测结果都是6,刚开始做深度学习,出现bug真是愁好几天,大神求解惑
http://blog.csdn.net/sparta_117/article/details/66965760
参考:基于tensorflow的MNIST手写字识别
http://www.jianshu.com/p/4195577585e6
问题得到解决,是resize图片时出错
楼主,我用的PIL.Image模块,也碰到了同样的问题,不管写入什么都是5。代码如下:
from PIL import Image
import numpy as np
import tensorflow as tf
import mnist_backward
import mnist_forward
def restore_model(testPicArr):
with tf.Graph().as_default() as tg:
x = tf.placeholder(tf.float32,[None,mnist_forward.INPUT_NODE])
y = mnist_forward.forward(x,None)
preValue = tf.argmax(y,1)
variable_averages = tf.train.ExponentialMovingAverage(mnist_backward.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess,ckpt.model_checkpoint_path)
preValue = sess.run(preValue,feed_dict={x:testPicArr})
return (preValue)
else:
print("No checkpoint file exist!")
return (-1)
def pre_pic(picName):
img = Image.open(picName)
reIm = img.resize((28,28),Image.ANTIALIAS)
im_arr = np.array(reIm.convert('L'))
threshold = 500
for i in range(28):
for j in range(28):
im_arr[i][j] = 255*im_arr[i][j]
if im_arr[i][j]<threshold:
im_arr[i][j] = 0
else:
im_arr[i][j] = 255
nm_arr = im_arr.reshape([1,784])
nm_arr = nm_arr.astype(np.float32)
img_ready = np.multiply(nm_arr,1.0/255.0)
return (img_ready)
def application():
testNum = input("input the number of test pictures :")
testNum = int(testNum)
for i in range(testNum):
testPic = input("the path of test pictures :")
testPicArr = pre_pic(testPic)
preValue = restore_model(testPicArr)
print("the prediction number is : ",preValue)
def main():
application()
if __name__ == "__main__":
main()
能解答下吗?
我已经找到原因了。一是:阈值threshol设错了,应该是50。另外是im_arr[i][j] = 255*im_arr[i][j]中应该是减号而不是乘号。