Question

我使用Keras为YOLO实现了自定义损失函数和模型。我正在使用Tensorflow作为后端。

import pickle
import tensorflow as tf
import numpy as np 
import matplotlib.pyplot as plt 
from keras.models import Sequential,load_model
from keras.layers import Dense,Conv2D,Activation,MaxPooling2D,Flatten
import keras as k
from keras import optimizers
import cv2

batch=12

sess= tf.Session()

#loss function
def yolo_loss(yTrue,yPred):
    coord=5
    noobj=0.5
    L_noobj=1
    L_obj=1
    if yTrue[6] == 1: 
       L_obj=0

    if yTrue[5] == 1:
       L_noobj=0

    w=coord*L_obj*(tf.square([tf.sqrt(yTrue[2])-tf.sqrt(yPred[2])])) 
    h=coord*L_obj*(tf.square([yTrue[3]-yPred[3]]))
    x=coord*L_obj*(tf.square([yTrue[0]-yPred[0]]))
    y=coord*L_obj*(tf.square([yTrue[1]-yPred[1]])) 
    no_obj=noobj*L_noobj*(tf.square([yTrue[6]-yPred[6]])) 
    obj=L_obj*(tf.square([yTrue[5]-yPred[5]])) 
    clss=L_obj*(tf.square([yTrue[4]-yPred[4]]))
    loss=w+h+x+y+no_obj+obj+clss
    return loss

def custom_loss(yTrue,yPred):
    loss=None
    for a in range(batch):
        loss_per_sample=0
        for b in range(4):
            for c in range(4):
                loss_per_sample += yolo_loss(yTrue[a,b,c,0:],yPred[a,b,c,0:])  
        if loss == None:
            loss=tf.stack(loss_per_sample)
        else:
            x=tf.stack(loss_per_sample)
            loss=tf.concat([loss,x],0)

    loss=tf.reshape(loss,[-1,1])      
    return loss 

#load data and labels 
x_train=pickle.load(open('data_image.pickle','rb'))
y_train=pickle.load(open('data_label.pickle','rb'))
test=pickle.load(open('test_image.pickle','rb'))


# model
model=Sequential()

model.add(Conv2D(16,(7,7),input_shape=x_train.shape[1:],padding="same"))
model.add(Activation("relu"))
model.add(MaxPooling2D((2,2)))

model.add(Conv2D(32,(3,3),padding="same"))
model.add(Activation("relu"))
model.add(MaxPooling2D((2,2)))

model.add(Conv2D(64,(3,3),padding="same"))
model.add(Activation("relu"))
model.add(MaxPooling2D((2,2)))

model.add(Conv2D(128,(3,3),padding="same"))
model.add(Activation("relu"))
model.add(MaxPooling2D((2,2)))

model.add(Conv2D(512,(3,3),padding="same"))
model.add(Activation("relu"))
model.add(MaxPooling2D((2,2)))

model.add(Conv2D(512,(3,3),padding="same"))
model.add(Activation("relu"))

model.add(Conv2D(1024,(3,3),padding="same"))
model.add(Activation("relu"))

model.add(Conv2D(7,(3,3),padding="same"))
model.add(Activation("relu"))

adam = optimizers.adam(lr=0.001)
model.compile(loss=custom_loss,optimizer=adam,metrics=["accuracy"]) 


model.fit(x_train,y_train,batch_size=batch,epochs=100)

model.save('yolo.model')

当我训练模型时，损失值将变为NAN。但是在自定义损失函数的“ W”和“ h”中删除tf.sqrt（）之后，损失几乎为零。但是问题是边界框的“ W”和“ h”值始终为零。我认为tf.sqrt（）函数中有一些东西。请有人能告诉我这是怎么回事。

Answer 1

我认为这是一种除以零误差的问题，我在使用Yolo和darkflow进行玩家检测时遇到了这个问题，我要解决的一件事是对批量大小和学习率进行了一些调整。

Answer 2

您在最后一层使用relu，这是不期望的。这可能会导致梯度消失。

此外，在使用sqrt函数之前，请做一些检查，例如负值。

model.add(Conv2D(7,(3,3),padding="same"))
model.add(Activation("relu"))

adam = optimizers.adam(lr=0.001)
model.compile(loss=custom_loss,optimizer=adam,metrics=["accuracy"])

训练定制YOLO模型时损失归于NAN

2 个答案: