问题描述
我正在尝试制作姿势估计模型，因此正在编写自己的损失函数，因为我没有找到任何好的解决方案，并且我想学习新的东西。
我认为最好的选择是使用自动编码器网络生成热图。对于我的标签，我使用从关键点生成的热图，作为输出，我使用具有张量的张量，形状为（1，640，640，16）16个热图，每个热图用于一个关键点。
我不知道训练这样的网络的最佳方法是什么（甚至不知道架构是否正确），但是对于损失函数，我唯一能想到的就是互相关。
from tensorflow import keras
import cv2
from keras.models import Model
from keras.callbacks import TensorBoard
from keras.models import load_model
import math
import os
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
from keras.models import Sequential
from keras.layers import Input,Add,Dense,Activation,ZeroPadding2D,Batchnormalization,Flatten,Conv2D,AveragePooling2D,MaxPooling2D,GlobalMaxPooling2D,UpSampling2D
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import RMSprop,Adam,SGD,Adagrad,Adadelta,Adamax,Nadam
from keras.applications import xception
import tensorflow.keras.backend as K
input_img = Input(shape=(640,640,1))
x1 = Conv2D(32,(3,3),activation='relu',padding='same')(input_img)
m1 = MaxPooling2D((2,2),padding='same')(x1)
x2 = Conv2D(32,padding='same')(m1)
m2 = MaxPooling2D((2,padding='same')(x2)
x3 = Conv2D(32,padding='same')(m2)
m3 = MaxPooling2D((2,padding='same')(x3)
x4 = Conv2D(32,padding='same')(m3)
m4 = MaxPooling2D((2,padding='same')(x4)
x5 = Conv2D(32,padding='same')(m4)
encoded = MaxPooling2D((2,padding='same')(x5)
y00 = Conv2D(32,padding='same')(encoded)
u00 = UpSampling2D((2,2))(y00)
y0 = Conv2D(32,padding='same')(u00)
u0 = UpSampling2D((2,2))(y0)
x4 = Conv2D(32,padding='same')(x4)
w = Add()([u0,x4])
y1 = Conv2D(32,padding='same')(w)
u1 = UpSampling2D((2,2))(y1)
x3 = Conv2D(32,padding='same')(x3)
w = Add()([u1,x3])
y2 = Conv2D(32,padding='same')(w)
u2 = UpSampling2D((2,2))(y2)
x2 = Conv2D(32,padding='same')(x2)
w = Add()([u2,x2])
y3 = Conv2D(32,padding='same')(w)
u3 = UpSampling2D((2,2))(y3)
x1 = Conv2D(32,padding='same')(x1)
w = Add()([u3,x1])
decoded = Conv2D(16,activation='sigmoid',padding='same')(w)
autoencoder = Model(input_img,decoded)
images = np.random.rand(10,640)
labels = []
points = np.random.randint(0,(10,16,640))
def make_dataset_gaussian(size,fwhm,center):
x = np.arange(0,size,1,float)
y = x[:,np.newaxis]
x0 = center[0]
y0 = center[1]
return np.exp(-4*np.log(2) * ((x-x0)**2 + (y-y0)**2) / fwhm**2)
for label in points:
tmp_label = []
for keypoint in label:
tmp_label.append(make_dataset_gaussian(640,15,[keypoint[0],keypoint[1]]))
labels.append(np.array(tmp_label).reshape((1,16)))
dataset = tf.data.Dataset.from_tensor_slices((images,labels))
def argmax_2d(tensor):
flat_tensor = tf.reshape(tensor,(tf.shape(tensor)[0] ** 2,))
argmax = tf.cast(tf.argmax(flat_tensor),tf.int32)
argmax_x = argmax // tf.shape(tensor)[0]
argmax_y = argmax % tf.shape(tensor)[0]
return tf.stack((argmax_x,argmax_y))
def cross_correlation(a,b):
a = tf.cast(a,tf.complex64)
b = tf.cast(b,tf.complex64)
fft_x = tf.signal.fft2d(a)
fft_y = tf.signal.fft2d(b)
return tf.math.real(tf.signal.ifft2d(fft_x*fft_y))
def my_loss(x_true,y_predicted):
x_true = tf.reshape(x_true,(1,640))
y_predicted = tf.reshape(y_predicted,640))
error = tf.cast(0,tf.float64)
for y in range(len(x_true)):
for x in range(len(x_true[y])):
cross = cross_correlation(x_true[y][x],y_predicted[y][x])
position = argmax_2d(cross)
error += tf.cast(position[0] + position[1],tf.float64)
return error
autoencoder.summary()
autoencoder.compile(optimizer='adam',loss=my_loss,metrics=['accuracy'])
autoencoder.fit(dataset.batch(1),epochs=10,batch_size=1)
ValueError: in user code:
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function *
return step_function(self,iterator)
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step,args=(data,))
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn,args=args,kwargs=kwargs)
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn,args,kwargs)
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
return fn(*args,**kwargs)
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step **
outputs = model.train_step(data)
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\keras\engine\training.py:756 train_step
_minimize(self.distribute_strategy,tape,self.optimizer,loss,d:\human-pose-model\venv\lib\site-packages\tensorflow\python\keras\engine\training.py:2736 _minimize
gradients = optimizer._aggregate_gradients(zip(gradients,# pylint: disable=protected-access
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\keras\optimizer_v2\optimizer_v2.py:562 _aggregate_gradients
filtered_grads_and_vars = _filter_grads(grads_and_vars)
d:\human-pose-model\venv\lib\site-packages\tensorflow\python\keras\optimizer_v2\optimizer_v2.py:1270 _filter_grads
raise ValueError("No gradients provided for any variable: %s." %
ValueError: No gradients provided for any variable: ['conv2d/kernel:0','conv2d/bias:0','conv2d_1/kernel:0','conv2d_1/bias:0','conv2d_2/kernel:0','conv2d_2/bias:0','conv2d_3/kernel:0','conv2d_3/bias:0','conv2d_4/kernel:0','conv2d_4/bias:0','conv2d_5/kernel:0','conv2d_5/bias:0','conv2d_6/kernel:0','conv2d_6/bias:0','conv2d_7/kernel:0','conv2d_7/bias:0','conv2d_8/kernel:0','conv2d_8/bias:0','conv2d_9/kernel:0','conv2d_9/bias:0','conv2d_10/kernel:0','conv2d_10/bias:0','conv2d_11/kernel:0','conv2d_11/bias:0','conv2d_12/kernel:0','conv2d_12/bias:0','conv2d_13/kernel:0','conv2d_13/bias:0','conv2d_14/kernel:0','conv2d_14/bias:0'].
我非常确定错误是由tf.argmax()函数引起的，但是我找不到其他任何用于计算互相关损失的解决方案。
我正在使用Python 3.8.2和Tensorflow 2.3.0
解决方法
暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！
如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@）