本案例參考課程:百度架構師手把手教深度學習的內容。 主要目的爲練習vgg動態圖的PaddlePaddle實現。git
本案例已經在AISTUDIO共享,連接爲:算法
https://aistudio.baidu.com/aistudio/projectdetail/244766網絡
數據集iChallenge-PM:架構
數據集圖片 iChallenge-PM中既有病理性近視患者的眼底圖片,也有非病理性近視患者的圖片,命名規則以下:app
病理性近視(PM):文件名以P開頭dom
非病理性近視(non-PM):ide
高度近似(high myopia):文件名以H開頭函數
正常眼睛(normal):文件名以N開頭學習
咱們將病理性患者的圖片做爲正樣本,標籤爲1; 非病理性患者的圖片做爲負樣本,標籤爲0。從數據集中選取兩張圖片,經過LeNet提取特徵,構建分類器,對正負樣本進行分類,並將圖片顯示出來。測試
算法:
VGG VGG是當前最流行的CNN模型之一,2014年由Simonyan和Zisserman提出,其命名來源於論文做者所在的實驗室Visual Geometry Group。AlexNet模型經過構造多層網絡,取得了較好的效果,可是並無給出深度神經網絡設計的方向。VGG經過使用一系列大小爲3x3的小尺寸卷積核和pooling層構造深度卷積神經網絡,並取得了較好的效果。VGG模型由於結構簡單、應用性極強而廣受研究者歡迎,尤爲是它的網絡結構設計方法,爲構建深度神經網絡提供了方向。
圖3 是VGG-16的網絡結構示意圖,有13層卷積和3層全鏈接層。VGG網絡的設計嚴格使用3×33\times 33×3的卷積層和池化層來提取特徵,並在網絡的最後面使用三層全鏈接層,將最後一層全鏈接層的輸出做爲分類的預測。 在VGG中每層卷積將使用ReLU做爲激活函數,在全鏈接層以後添加dropout來抑制過擬合。使用小的卷積核可以有效地減小參數的個數,使得訓練和測試變得更加有效。好比使用兩層3×33\times 33×3卷積層,能夠獲得感覺野爲5的特徵圖,而比使用5×55 \times 55×5的卷積層須要更少的參數。因爲卷積核比較小,能夠堆疊更多的卷積層,加深網絡的深度,這對於圖像分類任務來講是有利的。VGG模型的成功證實了增長網絡的深度,能夠更好的學習圖像中的特徵模式。
關鍵代碼:
import os
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
from PIL import Image
DATADIR = '/home/aistudio/work/palm/PALM-Training400/PALM-Training400'
# 文件名以N開頭的是正常眼底圖片,以P開頭的是病變眼底圖片
file1 = 'N0012.jpg'
file2 = 'P0095.jpg'
# 讀取圖片
img1 = Image.open(os.path.join(DATADIR, file1))
img1 = np.array(img1)
img2 = Image.open(os.path.join(DATADIR, file2))
img2 = np.array(img2)
# 畫出讀取的圖片
plt.figure(figsize=(16, 8))
f = plt.subplot(121)
f.set_title('Normal', fontsize=20)
plt.imshow(img1)
f = plt.subplot(122)
f.set_title('PM', fontsize=20)
plt.imshow(img2)
plt.show()
In[3]
# 查看圖片形狀
img1.shape, img2.shape
((2056, 2124, 3), (2056, 2124, 3))
In[5]
#定義數據讀取器
import cv2
import random
import numpy as np
# 對讀入的圖像數據進行預處理
def transform_img(img):
# 將圖片尺寸縮放道 224x224
img = cv2.resize(img, (224, 224))
# 讀入的圖像數據格式是[H, W, C]
# 使用轉置操做將其變成[C, H, W]
img = np.transpose(img, (2,0,1))
img = img.astype('float32')
# 將數據範圍調整到[-1.0, 1.0]之間
img = img / 255.
img = img * 2.0 - 1.0
return img
# 定義訓練集數據讀取器
def data_loader(datadir, batch_size=10, mode = 'train'):
# 將datadir目錄下的文件列出來,每條文件都要讀入
filenames = os.listdir(datadir)
def reader():
if mode == 'train':
# 訓練時隨機打亂數據順序
random.shuffle(filenames)
batch_imgs = []
batch_labels = []
for name in filenames:
filepath = os.path.join(datadir, name)
img = cv2.imread(filepath)
img = transform_img(img)
if name[0] == 'H' or name[0] == 'N':
# H開頭的文件名錶示高度近似,N開頭的文件名錶示正常視力
# 高度近視和正常視力的樣本,都不是病理性的,屬於負樣本,標籤爲0
label = 0
elif name[0] == 'P':
# P開頭的是病理性近視,屬於正樣本,標籤爲1
label = 1
else:
raise('Not excepted file name')
# 每讀取一個樣本的數據,就將其放入數據列表中
batch_imgs.append(img)
batch_labels.append(label)
if len(batch_imgs) == batch_size:
# 當數據列表的長度等於batch_size的時候,
# 把這些數據看成一個mini-batch,並做爲數據生成器的一個輸出
imgs_array = np.array(batch_imgs).astype('float32')
labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
yield imgs_array, labels_array
batch_imgs = []
batch_labels = []
if len(batch_imgs) > 0:
# 剩餘樣本數目不足一個batch_size的數據,一塊兒打包成一個mini-batch
imgs_array = np.array(batch_imgs).astype('float32')
labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
yield imgs_array, labels_array
return reader
# 查看數據形狀
DATADIR = '/home/aistudio/work/palm/PALM-Training400/PALM-Training400'
train_loader = data_loader(DATADIR,
batch_size=10, mode='train')
data_reader = train_loader()
data = next(data_reader)
data[0].shape, data[1].shape
((10, 3, 224, 224), (10, 1))
In[6]
!pip install xlrd
import pandas as pd
df=pd.read_excel('/home/aistudio/work/palm/PALM-Validation-GT/PM_Label_and_Fovea_Location.xlsx')
df.to_csv('/home/aistudio/work/palm/PALM-Validation-GT/labels.csv',index=False)
#訓練和評估代碼
import os
import random
import paddle
import paddle.fluid as fluid
import numpy as np
DATADIR = '/home/aistudio/work/palm/PALM-Training400/PALM-Training400'
DATADIR2 = '/home/aistudio/work/palm/PALM-Validation400'
CSVFILE = '/home/aistudio/work/palm/PALM-Validation-GT/labels.csv'
# 定義訓練過程
def train(model):
with fluid.dygraph.guard():
print('start training ... ')
model.train()
epoch_num = 5
# 定義優化器
opt = fluid.optimizer.Momentum(learning_rate=0.001, momentum=0.9)
# 定義數據讀取器,訓練數據讀取器和驗證數據讀取器
train_loader = data_loader(DATADIR, batch_size=10, mode='train')
valid_loader = valid_data_loader(DATADIR2, CSVFILE)
for epoch in range(epoch_num):
for batch_id, data in enumerate(train_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
# 運行模型前向計算,獲得預測值
logits = model(img)
# 進行loss計算
loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label)
avg_loss = fluid.layers.mean(loss)
if batch_id % 10 == 0:
print("epoch: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, avg_loss.numpy()))
# 反向傳播,更新權重,清除梯度
avg_loss.backward()
opt.minimize(avg_loss)
model.clear_gradients()
model.eval()
accuracies = []
losses = []
for batch_id, data in enumerate(valid_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
# 運行模型前向計算,獲得預測值
logits = model(img)
# 二分類,sigmoid計算後的結果以0.5爲閾值分兩個類別
# 計算sigmoid後的預測機率,進行loss計算
pred = fluid.layers.sigmoid(logits)
loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label)
# 計算預測機率小於0.5的類別
pred2 = pred * (-1.0) + 1.0
# 獲得兩個類別的預測機率,並沿第一個維度級聯
pred = fluid.layers.concat([pred2, pred], axis=1)
acc = fluid.layers.accuracy(pred, fluid.layers.cast(label, dtype='int64'))
accuracies.append(acc.numpy())
losses.append(loss.numpy())
print("[validation] accuracy/loss: {}/{}".format(np.mean(accuracies), np.mean(losses)))
model.train()
# save params of model
fluid.save_dygraph(model.state_dict(), 'mnist')
# save optimizer state
fluid.save_dygraph(opt.state_dict(), 'mnist')
# 定義評估過程
def evaluation(model, params_file_path):
with fluid.dygraph.guard():
print('start evaluation .......')
#加載模型參數
model_state_dict, _ = fluid.load_dygraph(params_file_path)
model.load_dict(model_state_dict)
model.eval()
eval_loader = load_data('eval')
acc_set = []
avg_loss_set = []
for batch_id, data in enumerate(eval_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
# 計算預測和精度
prediction, acc = model(img, label)
# 計算損失函數值
loss = fluid.layers.cross_entropy(input=prediction, label=label)
avg_loss = fluid.layers.mean(loss)
acc_set.append(float(acc.numpy()))
avg_loss_set.append(float(avg_loss.numpy()))
# 求平均精度
acc_val_mean = np.array(acc_set).mean()
avg_loss_val_mean = np.array(avg_loss_set).mean()
print('loss={}, acc={}'.format(avg_loss_val_mean, acc_val_mean))
In[8]
# -*- coding:utf-8 -*-
# VGG模型代碼
import numpy as np
import paddle
import paddle.fluid as fluid
from paddle.fluid.layer_helper import LayerHelper
from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, FC
from paddle.fluid.dygraph.base import to_variable
# 定義vgg塊,包含多層卷積和1層2x2的最大池化層
class vgg_block(fluid.dygraph.Layer):
def __init__(self, name_scope, num_convs, num_channels):
"""
num_convs, 卷積層的數目
num_channels, 卷積層的輸出通道數,在同一個Incepition塊內,卷積層輸出通道數是同樣的
"""
super(vgg_block, self).__init__(name_scope)
self.conv_list = []
for i in range(num_convs):
conv_layer = self.add_sublayer('conv_' + str(i), Conv2D(self.full_name(),
num_filters=num_channels, filter_size=3, padding=1, act='relu'))
self.conv_list.append(conv_layer)
self.pool = Pool2D(self.full_name(), pool_stride=2, pool_size = 2, pool_type='max')
def forward(self, x):
for item in self.conv_list:
x = item(x)
return self.pool(x)
class VGG(fluid.dygraph.Layer):
def __init__(self, name_scope, conv_arch=((2, 64),
(2, 128), (3, 256), (3, 512), (3, 512))):
super(VGG, self).__init__(name_scope)
self.vgg_blocks=[]
iter_id = 0
# 添加vgg_block
# 這裏一共5個vgg_block,每一個block裏面的卷積層數目和輸出通道數由conv_arch指定
for (num_convs, num_channels) in conv_arch:
block = self.add_sublayer('block_' + str(iter_id),
vgg_block(self.full_name(), num_convs, num_channels))
self.vgg_blocks.append(block)
iter_id += 1
self.fc1 = FC(self.full_name(),
size=4096,
act='relu')
self.drop1_ratio = 0.5
self.fc2= FC(self.full_name(),
size=4096,
act='relu')
self.drop2_ratio = 0.5
self.fc3 = FC(self.full_name(),
size=1,
)
def forward(self, x):
for item in self.vgg_blocks:
x = item(x)
x = fluid.layers.dropout(self.fc1(x), self.drop1_ratio)
x = fluid.layers.dropout(self.fc2(x), self.drop2_ratio)
x = self.fc3(x)
return x
with fluid.dygraph.guard():
model = VGG("VGG")
train(model)
start training ...
epoch: 0, batch_id: 0, loss is: [0.7242754]
epoch: 0, batch_id: 10, loss is: [0.6634571]
epoch: 0, batch_id: 20, loss is: [0.7898234]
epoch: 0, batch_id: 30, loss is: [0.60537547]
[validation] accuracy/loss: 0.9424999952316284/0.35623037815093994
epoch: 1, batch_id: 0, loss is: [0.31599292]
epoch: 1, batch_id: 10, loss is: [0.1198744]
epoch: 1, batch_id: 20, loss is: [0.46862125]
epoch: 1, batch_id: 30, loss is: [0.2300901]
[validation] accuracy/loss: 0.92249995470047/0.2342415601015091
epoch: 2, batch_id: 0, loss is: [0.22039299]
epoch: 2, batch_id: 10, loss is: [0.65977865]
epoch: 2, batch_id: 20, loss is: [0.37409317]
epoch: 2, batch_id: 30, loss is: [0.1841044]
[validation] accuracy/loss: 0.9325000643730164/0.22097690403461456
epoch: 3, batch_id: 0, loss is: [0.4992897]
epoch: 3, batch_id: 10, loss is: [0.31177607]
epoch: 3, batch_id: 20, loss is: [0.1721839]
epoch: 3, batch_id: 30, loss is: [0.38319916]
[validation] accuracy/loss: 0.9199999570846558/0.20679759979248047
epoch: 4, batch_id: 0, loss is: [0.20610766]
epoch: 4, batch_id: 10, loss is: [0.06688808]
epoch: 4, batch_id: 20, loss is: [0.3352648]
epoch: 4, batch_id: 30, loss is: [0.28062168]
[validation] accuracy/loss: 0.9149999618530273/0.21788272261619568
with fluid.dygraph.guard():
model = VGG("VGG")
train(model)