Question

这是我第一次在cnn中训练模型并预测结果，但是我输入的图像的值相同。这是我的代码

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.optimizers import Adam
from keras.layers.normalization import BatchNormalization
from keras.utils import np_utils
from keras.layers import Conv2D, MaxPooling2D, ZeroPadding2D, 
GlobalAveragePooling2D
from keras.layers.advanced_activations import LeakyReLU 
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
classifier=Sequential()
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train/=255
X_test/=255
number_of_classes = 10
Y_train = np_utils.to_categorical(y_train, number_of_classes)
Y_test = np_utils.to_categorical(y_test, number_of_classes)
classifier.add(Convolution2D(32,3,3,input_shape= 
(28,28,1),activation='relu'))
classifier.add(BatchNormalization(axis=-1))
classifier.add(MaxPooling2D(pool_size=(2,2)))

classifier.add(Convolution2D(32,3,3,activation='relu'))
classifier.add(BatchNormalization(axis=-1))
classifier.add(MaxPooling2D(pool_size=(2,2)))

classifier.add(Flatten())

classifier.add(Dense(output_dim=256,activation='relu'))
classifier.add(BatchNormalization())
classifier.add(Dense(output_dim=10,activation='softmax'))

classifier.compile(optimizer='adam',loss='categorical_crossentropy',metrics=            
['accuracy'])
gen = ImageDataGenerator(rotation_range=8, width_shift_range=0.08,         
shear_range=0.3, height_shift_range=0.08, zoom_range=0.08)

test_gen = ImageDataGenerator()
train_generator = gen.flow(X_train, Y_train, batch_size=64)
test_generator = test_gen.flow(X_test, Y_test, batch_size=64)
classifier.fit_generator(train_generator, steps_per_epoch=60000, epochs=1, 
                validation_data=test_generator, validation_steps=10000)
import cv2
image = cv2.imread("pitrain.png")
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY) # grayscale
ret,thresh = cv2.threshold(gray,150,255,cv2.THRESH_BINARY_INV) 
#threshold
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS,(3,3))
dilated = cv2.dilate(thresh,kernel,iterations = 13) # dilate
im2,contours, hierarchy =             
cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE) 
# get contours
# for each contour found, draw a rectangle around it on original image
for contour in contours:

# get rectangle bounding contour

[x,y,w,h] = cv2.boundingRect(contour)
# discard areas that are too large

if h>300 and w>300:

    continue
# discard areas that are too small

if h<40 or w<40:

    continue
# draw rectangle around contour on original image

cv2.rectangle(image,(x,y),(x+w,y+h),(255,0,255),2)
image.shape
image=image[:,:,:1]
newimg = cv2.resize(image,(28,28))
img.shape
img = np.reshape(newimg,[1,28,28,1])
cv2.imshow("screen",img)
classifier.predict(img)

我得到的输出是零的数组，在第三个位置有1。这是我从https://www.quora.com/How-do-I-extract-a-particular-object-from-images-using-OpenCV

复制轮廓部分的地方

Epoch等于1，因为我只想测试我的模型，但仍然准确率高于99％

为cnn中的所有预测获得相同的结果

0 个答案: