Aerial Cactus Identification(空中仙人掌鉴定)

本文主要是介绍Aerial Cactus Identification(空中仙人掌鉴定)，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

Aerial Cactus Identification 空中仙人掌鉴定

二分类问题

方案一：

import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import os,cv2
from IPython.display import Image
from keras.preprocessing import image
from keras import optimizers
from keras import layers,models
from keras.applications.imagenet_utils import preprocess_input
import matplotlib.pyplot as plt
import seaborn as sns
from keras import regularizers
from keras.preprocessing.image import ImageDataGenerator
from keras.applications.vgg16 import VGG16import numpy as nptrain_path=r'.\input\train'
test_path=r'.\input\test'
train=pd.read_csv(r'.\input\train.csv')
test_df=pd.read_csv(r'.\input\sample_submission.csv')
train.has_cactus=train.has_cactus.astype(str)#Data preparation
datagen=ImageDataGenerator(rescale=1./255)
batch_size=150train_generator=datagen.flow_from_dataframe(dataframe=train[:15001],directory=train_path,x_col='id',y_col='has_cactus',class_mode='binary',batch_size=batch_size,target_size=(150,150))validation_generator=datagen.flow_from_dataframe(dataframe=train[15000:],directory=train_path,x_col='id',y_col='has_cactus',class_mode='binary',batch_size=50,target_size=(150,150))def cnn_model():model=models.Sequential()model.add(layers.Conv2D(32,(3,3),activation='relu',input_shape=(150,150,3)))model.add(layers.MaxPool2D((2,2)))model.add(layers.Conv2D(64,(3,3),activation='relu',input_shape=(150,150,3)))model.add(layers.MaxPool2D((2,2)))model.add(layers.Conv2D(128,(3,3),activation='relu',input_shape=(150,150,3)))model.add(layers.MaxPool2D((2,2)))model.add(layers.Conv2D(128,(3,3),activation='relu',input_shape=(150,150,3)))model.add(layers.MaxPool2D((2,2)))model.add(layers.Flatten())model.add(layers.Dense(512,activation='relu'))model.add(layers.Dense(1,activation='sigmoid'))model.compile(loss='binary_crossentropy',optimizer=optimizers.rmsprop(),metrics=['acc'])epochs=100history=model.fit_generator(train_generator,steps_per_epoch=100,epochs=epochs,validation_data=validation_generator,validation_steps=50)X_tst = []Test_imgs = []for img_id in os.listdir(test_path):X_tst.append(cv2.imread(os.path.join(test_path,img_id)))Test_imgs.append(img_id)X_tst = np.asarray(X_tst)X_tst = X_tst.astype('float32')X_tst /= 255test_predictions = model.predict(X_tst)sub_df = pd.DataFrame(test_predictions, columns=['has_cactus'])sub_df['has_cactus'] = sub_df['has_cactus'].apply(lambda x: 1 if x > 0.75 else 0)sub_df['id'] = ''cols = sub_df.columns.tolist()cols = cols[-1:] + cols[:-1]sub_df=sub_df[cols]for i, img in enumerate(Test_imgs):sub_df.set_value(i,'id',img)sub_df.to_csv('result2.csv',index=False)def vgg16_model():passif __name__=='__main__':cnn_model()

方案二：VGG16迁移学习

import cv2
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import json
import os
from tqdm import tqdm, tqdm_notebook
from keras.models import Sequential
from keras.layers import Activation, Dropout, Flatten, Dense
from keras.applications import VGG16
from keras.optimizers import Adam
import ostrain_path=r'.\input\train'
test_path=r'.\input\test'
train_df=pd.read_csv(r'.\input\train.csv')
test_df=pd.read_csv(r'.\input\sample_submission.csv')vgg16_net = VGG16(weights='imagenet',include_top=False,input_shape=(32, 32, 3))vgg16_net.trainable=Falsemodel = Sequential()
model.add(vgg16_net)
model.add(Flatten())
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))model.compile(loss='binary_crossentropy',optimizer=Adam(lr=1e-5),metrics=['accuracy'])X_tr = []
Y_tr = []
imges = train_df['id'].values
for img_id in imges:X_tr.append(cv2.imread(os.path.join(train_path,img_id)))Y_tr.append(train_df[train_df['id'] == img_id]['has_cactus'].values[0])
X_tr = np.asarray(X_tr)
X_tr = X_tr.astype('float32')
X_tr /= 255
Y_tr = np.asarray(Y_tr)batch_size = 32
nb_epoch = 1000history = model.fit(X_tr, Y_tr,batch_size=batch_size,epochs=nb_epoch,validation_split=0.1,shuffle=True,verbose=2)"""
with open('history.json', 'w') as f:json.dump(history.history, f)history_df = pd.DataFrame(history.history)
history_df[['loss', 'val_loss']].plot()
history_df[['acc', 'val_acc']].plot()
plt.show()
"""X_tst = []
Test_imgs = []
for img_id in os.listdir(test_path):X_tst.append(cv2.imread(os.path.join(test_path,img_id)))Test_imgs.append(img_id)
X_tst = np.asarray(X_tst)
X_tst = X_tst.astype('float32')
X_tst /= 255test_predictions = model.predict(X_tst)sub_df = pd.DataFrame(test_predictions, columns=['has_cactus'])
sub_df['has_cactus'] = sub_df['has_cactus'].apply(lambda x: 1 if x > 0.75 else 0)sub_df['id'] = ''
cols = sub_df.columns.tolist()
cols = cols[-1:] + cols[:-1]
sub_df=sub_df[cols]
for i, img in enumerate(Test_imgs):sub_df.set_value(i,'id',img)sub_df.to_csv('result2.csv',index=False)

我的方案：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import seaborn as sns
import itertools
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrixfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding
from keras.models import Sequential
from keras.models import load_model
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D
from keras.optimizers import RMSprop
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ReduceLROnPlateau
import cv2
import os
from keras.callbacks import EarlyStoppingtrain_path=r'.\input\train'
test_path=r'.\input\test'
train_df=pd.read_csv(r'.\input\train.csv')
test_df=pd.read_csv(r'.\input\sample_submission.csv')X_train=[]
Y_train=[]
for i in range(len(train_df)):img_path=os.path.join(train_path,train_df.id[i])image=np.array(cv2.imread(img_path))X_train.append(image)Y_train.append(train_df.has_cactus[i])X_train=np.array(X_train)/255.0
Y_train=np.array(Y_train)
Y_train=to_categorical(Y_train,num_classes=2)
# Set the random seed
random_seed = 2# Split the train and the validation set for the fitting
X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=random_seed)model_name='cnn_model.h5'
def train():# Define the modelmodel = Sequential()model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same',activation='relu', input_shape=(32, 32, 3)))model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same',activation='relu'))model.add(MaxPool2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same',activation='relu'))model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same',activation='relu'))model.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))model.add(Dropout(0.25))model.add(Flatten())model.add(Dense(256, activation="relu"))model.add(Dropout(0.5))model.add(Dense(2, activation="softmax"))print(model.summary())# Define the optimizeroptimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)# Compile the modelmodel.compile(optimizer=optimizer, loss="categorical_crossentropy", metrics=["accuracy"])# Set a learning rate annealerlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc',patience=3,verbose=1,factor=0.5,min_lr=0.00001)epochs = 300  # Turn epochs to 30 to get 0.9967 accuracybatch_size = 32# Data augmentationdatagen = ImageDataGenerator(featurewise_center=False,  # set input mean to 0 over the datasetsamplewise_center=False,  # set each sample mean to 0featurewise_std_normalization=False,  # divide inputs by std of the datasetsamplewise_std_normalization=False,  # divide each input by its stdzca_whitening=False,  # apply ZCA whiteningrotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)zoom_range=0.1,  # Randomly zoom imagewidth_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)horizontal_flip=False,  # randomly flip imagesvertical_flip=False)  # randomly flip imagesdatagen.fit(X_train)el = EarlyStopping(min_delta=0.001, patience=5)# Fit the modelhistory = model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size),epochs=epochs, validation_data=(X_val, Y_val),verbose=2, steps_per_epoch=X_train.shape[0] // batch_size, callbacks=[learning_rate_reduction,el])model.save(model_name)# Plot the loss and accuracy curves for training and validationfig, ax = plt.subplots(2, 1)ax[0].plot(history.history['loss'], color='b', label="Training loss")ax[0].plot(history.history['val_loss'], color='r', label="validation loss", axes=ax[0])legend = ax[0].legend(loc='best', shadow=True)ax[1].plot(history.history['acc'], color='b', label="Training accuracy")ax[1].plot(history.history['val_acc'], color='r', label="Validation accuracy")legend = ax[1].legend(loc='best', shadow=True)plt.show()def test():X_test=[]for i in range(len(test_df)):img_path = os.path.join(test_path, test_df.id[i])image = np.array(cv2.imread(img_path))X_test.append(image)X_test = np.array(X_test) / 255.0model=load_model(model_name)Y_pred=model.predict(X_test)Y_pred=np.argmax(Y_pred,axis=1)test_df.has_cactus=Y_predtest_df.to_csv('result.csv',index=False)if __name__=='__main__':test()