keras-多标签分类

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from keras.layers.core import Dense,Activation,Dropout,Flatten
from keras.layers.advanced_activations import PReLU
from keras.layers.convolutional import Convolution2D,MaxPooling2D
from keras.optimizers import SGD,Adadelta,Adagrad
from keras.utils import np_utils,generic_utils
import random
np.random.seed(1024)
from PIL import Image
from keras.models import Sequential
import time
from keras.layers import LSTM
import math
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
from keras import optimizers
import os
from keras.preprocessing.image import ImageDataGenerator
from keras import backend as K
from keras.models import Sequential
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.layers.core import Activation
from keras.layers.core import Flatten
from keras.layers.core import Dropout
from keras.layers.core import Dense
from keras import backend as K

class SmallerVGGNet:
    @staticmethod
    def build(width,height,depth,classes,finalAct="softmax"):
        #initialize the model along with the input shape to be channels last and the channels dimension itself
        model = Sequential()
        inputShape = (height,width,depth)
        chanDim = -1
        #if we are using "channel first",update the input shape and channels dimension
        if K.image_data_format()=='channels_first':
            inputShape = (depth,height,width)
            chanDim = 1
            # CONV => RELU => POOL
            model.add(Conv2D(32, (3, 3), padding="same",
                             input_shape=inputShape))
            model.add(Activation("relu"))
            model.add(BatchNormalization(axis=chanDim))
            model.add(MaxPooling2D(pool_size=(3, 3)))
            model.add(Dropout(0.25))
            # (CONV => RELU) * 2 => POOL
            model.add(Conv2D(64, (3, 3), padding="same"))
            model.add(Activation("relu"))
            model.add(BatchNormalization(axis=chanDim))
            model.add(Conv2D(64, (3, 3), padding="same"))
            model.add(Activation("relu"))
            model.add(BatchNormalization(axis=chanDim))
            model.add(MaxPooling2D(pool_size=(2, 2)))
            model.add(Dropout(0.25))

            # (CONV => RELU) * 2 => POOL
            model.add(Conv2D(128, (3, 3), padding="same"))
            model.add(Activation("relu"))
            model.add(BatchNormalization(axis=chanDim))
            model.add(Conv2D(128, (3, 3), padding="same"))
            model.add(Activation("relu"))
            model.add(BatchNormalization(axis=chanDim))
            model.add(MaxPooling2D(pool_size=(2, 2)))
            model.add(Dropout(0.25))
            # first (and only) set of FC => RELU layers
            model.add(Flatten())
            model.add(Dense(1024))
            model.add(Activation("relu"))
            model.add(BatchNormalization())
            model.add(Dropout(0.5))

            # use a *softmax* activation for single-label classification
            # and *sigmoid* activation for multi-label classification
            model.add(Dense(classes))
            model.add(Activation(finalAct))

            # return the constructed network architecture
            return model




from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam
from keras.preprocessing.image import img_to_array
from sklearn.preprocessing import MultiLabelBinarizer
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from imutils import paths
import numpy as np
import argparse
import random
import pickle
import cv2
import os


# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True,
	help="path to input dataset (i.e., directory of images)")
ap.add_argument("-m", "--model", required=True,
	help="path to output model")
ap.add_argument("-l", "--labelbin", required=True,
	help="path to output label binarizer")
ap.add_argument("-p", "--plot", type=str, default="plot.png",
	help="path to output accuracy/loss plot")
args = vars(ap.parse_args())


'''
--dataset : The path to our dataset.
--model : The path to our output #serialized Keras model.
--labelbin : The path to our output multi-label binarizer object.
--plot : The path to our output plot of training loss and accuracy.
'''

#intialize the number of epochs to train for,intial learning rate,batch size and image dimensions
epochs = 75
init_lr = 1e-3
bs = 32
image_dims = (96,96,3)

#grab the image pths and randomly shuffle them
print("[Info] loading images...")
imagePaths = sorted(list(paths.list_images(args["dataset"])))
random.seed(42)
random.shuffle(imagePaths)

#initizlize the data and labels
data = []
labels = []

#loop over the input images
for imagePath in imagePaths:
    #load the image ,pre-proces it and store it in the data list
    image = cv2.imread(imagePath)
    image = cv2.resize(image,(image_dims[1],image_dims[0]))
    image = img_to_array(image)
    data.append(image)

#scale the raw pixel intensities to the range[0,1

data = np.array(data,dtype="float")/255.0
labels = np.array(labels)
print("[Info] data matrix:{} images(:.2f)MB".format(len(imagePaths),data.nbytes/(1024*1000.0)))

#二值化标签
print("[Info] class labels:")
mlb = MultiLabelBinarizer()
labels = mlb.fit_transform(labels)

#loop over each of the possible class labels and show them
for (i,label) in enumerate(mlb.classes_):
    print("{}.{}".format(i+1,label))


(trainX, testX, trainY, testY) = train_test_split(data,
	labels, test_size=0.2, random_state=42)

#图像增强
aug = ImageDataGenerator(rotation_range=25,width_shift_range=0.1,height_shift_range=0.1,shear_range=0.2,zoom_range=0.2,horizontal_flip=True,fill_mode="nearest")

#接下来就是建立模型了
#initialize the model using a sigmoid activation as the final layer in the network so we can perform multi-label classification
print("[Info] compilig model...")
model = SmallerVGGNet.build(width=image_dims[1],height=image_dims[0],depth=image_dims[2],classes=len(mlb.classes_),finalAct="sigmoid")

#初始化优化器
opt = Adam(lr=init_lr,decay=init_lr/epochs)


# compile the model using binary cross-entropy rather than
# categorical cross-entropy -- this may seem counterintuitive for
# multi-label classification, but keep in mind that the goal here
# is to treat each output label as an independent Bernoulli
# distribution
model.compile(loss="binary_crossentropy", optimizer=opt,
	metrics=["accuracy"])

#train the network
print("[Info] training network...")
H = model.fit_generator(aug.flow(trainX,trainY,batch_size=bs,validation_data=(testX,testY),steps_per_epoch=len(trainX)//bs,epochs=epochs,verbose=1))

#保存模型
print("[Info] serializing network...")

model.save(args["model"])

# save the multi-label binarizer to disk
print("[INFO] serializing label binarizer...")
f = open(args["labelbin"], "wb")
f.write(pickle.dumps(mlb))
f.close()

# plot the training loss and accuracy
plt.style.use("ggplot")
plt.figure()
N = epochs
plt.plot(np.arange(0, N), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, N), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, N), H.history["acc"], label="train_acc")
plt.plot(np.arange(0, N), H.history["val_acc"], label="val_acc")
plt.title("Training Loss and Accuracy")
plt.xlabel("Epoch #")
plt.ylabel("Loss/Accuracy")
plt.legend(loc="upper left")
plt.savefig(args["plot"])



'''
python GenderTrain.py --dataset dataset --model fashion.model --labelbin mlb.pickle
'''

# -*- coding: utf-8 -*-
"""
Created on 2019/5/25 17:00
@Author: Johnson
@Email:[email protected]
@File: 3-classify.py
"""
from keras.preprocessing.image import img_to_array
from keras.models import load_model
import numpy as np
import argparse
import imutils
import pickle
import cv2
import os


#constuct the argument parse and parse the arguments

ap = argparse.ArgumentParser()
ap.add_argument("-m","--model",required=True,help="path to trained model model")
ap.add_argument("-l","--labelbin",required=True,help="path to label binarizer")
ap.add_argument("-i","--image",required=True,help="path to input image")

args = vars(ap.parse_args())

#load the image
image = cv2.imread(args["image"])
output = imutils.resize(image,width=400)

#pre-process the image for classification
image = cv2.resize(image,(96,96))
image = image.astype("float")/255.0
image = img_to_array(image)
image = np.expand_dims(image,axis=0)

#load the trained network and the multi-label
print("[Info] loading network...")
model = load_model(args["model"])
mlb = pickle.load(open(args["labelbin"],"rb").read())

#classify the input image then find the indexex of the two class
proba = model.predict(image)[0]
idxs = np.argsort(proba)[::-1][:2]

#loop over the indexes of the high confidence class labels
for (i,j) in enumerate(idxs):
    #build the lable and draw the label on the image
    label = "{}:{:.2f}%".format(mlb.class_[j],proba[j]*100)
    cv2.putText(output,label,(10,(0*30)+25),cv2.FONT_HERSHEY_SIMPLEX,0.7,(0,255,0),2)

# show the probabilities for each of the individual labels
for (label, p) in zip(mlb.classes_, proba):
    print("{}: {:.2f}%".format(label, p * 100))

# show the output image
cv2.imshow("Output", output)
cv2.waitKey(0)


'''
python classify.py --model fashion.model --labelbin mlb.pickle \
	--image examples/example_01.jpg
'''