grisel-davy/Fresque-SETI
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Initial commit

Browse source
This commit is contained in:
grisel-davy 2021-01-08 19:41:57 +01:00
parent 83414655b0
commit 756b0a190a
5 changed files with 2340 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

505
Apprentissage_MSELoss_avec_GPU.ipynb Executable file
View file

File diff suppressed because one or more lines are too long

424
Apprentissage_MSELoss_avec_GPU.py Normal file
View file

@ -0,0 +1,424 @@
#!/usr/bin/env python
# coding: utf-8
# In[1]:
#Tous les codes sont basés sur l'environnement suivant
#python 3.7
#opencv 3.1.0
#pytorch 1.4.0
import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import cv2
import matplotlib.pyplot as plt
import numpy as np
import random
import math
import pickle
import random
from PIL import Image
import sys
# In[3]:
#Les fonctions dans ce bloc ne sont pas utilisées par le réseau, mais certaines fonctions d'outils
def tensor_imshow(im_tensor,cannel):
b,c,h,w=im_tensor.shape
if c==1:
plt.imshow(im_tensor.squeeze().detach().numpy())
else:
plt.imshow(im_tensor.squeeze().detach().numpy()[cannel,:])
# Obtenez des données d'entraînement
# frag,vt=get_training_fragment(frag_size,image)
# frag est un patch carrée de taille (frag_size*frag_size) a partir du image(Son emplacement est aléatoire)
# vt est la vérité terrain de la forme Dirac.
def get_training_fragment(frag_size,im):
h,w,c=im.shape
n=random.randint(0,int(h/frag_size)-1)
m=random.randint(0,int(w/frag_size)-1)
shape=frag_size/4
vt_h=math.ceil((h+1)/shape)
vt_w=math.ceil((w+1)/shape)
vt=np.zeros([vt_h,vt_w])
vt_h_po=round((vt_h-1)*(n*frag_size/(h-1)+(n+1)*frag_size/(h-1))/2)
vt_w_po=round((vt_w-1)*(m*frag_size/(w-1)+(m+1)*frag_size/(w-1))/2)
vt[vt_h_po,vt_w_po]=1
vt = np.float32(vt)
vt=torch.from_numpy(vt.reshape(1,1,vt_h,vt_w))
return im[n*frag_size:(n+1)*frag_size,m*frag_size:(m+1)*frag_size,:],vt
# Cette fonction convertit l'image en variable de type Tensor.
# Toutes les données de calcul du réseau sont de type Tensor
# Img.shape=[Height,Width,Channel]
# Tensor.shape=[Batch,Channel,Height,Width]
def img2tensor(im):
im=np.array(im,dtype="float32")
tensor_cv = torch.from_numpy(np.transpose(im, (2, 0, 1)))
im_tensor=tensor_cv.unsqueeze(0)
return im_tensor
# Trouvez les coordonnées de la valeur maximale dans une carte de corrélation
# x,y=show_coordonnee(carte de corrélation)
def show_coordonnee(position_pred):
map_corre=position_pred.squeeze().detach().numpy()
h,w=map_corre.shape
max_value=map_corre.max()
coordonnee=np.where(map_corre==max_value)
return coordonnee[0].mean()/h,coordonnee[1].mean()/w
# Filtrer les patchs en fonction du nombre de pixels noirs dans le patch
# Si seuls les pixels non noirs sont plus grands qu'une certaine proportion(seuillage), revenez à True, sinon False
def test_fragment32_32(frag,seuillage):
a=frag[:,:,0]+frag[:,:,1]+frag[:,:,2]
mask = (a == 0)
arr_new = a[mask]
if arr_new.size/a.size<=(1-seuillage):
return True
else:
return False
# Ces deux fonctions permettent de sauvegarder le réseau dans un fichier
# ou de load le réseau stocké à partir d'un fichier
def save_net(file_path,net):
pkl_file = open(file_path, 'wb')
pickle.dump(net,pkl_file)
pkl_file.close()
def load_net(file_path):
pkl_file = open(file_path, 'rb')
net= pickle.load(pkl_file)
pkl_file.close()
return net
# In[4]:
# Les fonctions de ce bloc sont utilisées pour construire le réseau
# Créer un poids de type DeepMatch comme valeur initiale de Conv1 (non obligatoire)
def ini():
kernel=torch.zeros([8,3,3,3])
array_0=np.array([[1,2,1],[0,0,0],[-1,-2,-1]],dtype='float32')
array_1=np.array([[2,1,0],[1,0,-1],[0,-1,-2]],dtype='float32')
array_2=np.array([[1,0,-1],[2,0,-2],[1,0,-1]],dtype='float32')
array_3=np.array([[0,-1,-2],[1,0,-1],[2,1,0]],dtype='float32')
array_4=np.array([[-1,-2,-1],[0,0,0],[1,2,1]],dtype='float32')
array_5=np.array([[-2,-1,0],[-1,0,1],[0,1,2]],dtype='float32')
array_6=np.array([[-1,0,1],[-2,0,2],[-1,0,1]],dtype='float32')
array_7=np.array([[0,1,2],[-1,0,1],[-2,-1,0]],dtype='float32')
for i in range(3):
kernel[0,i,:]=torch.from_numpy(array_0)
kernel[1,i,:]=torch.from_numpy(array_1)
kernel[2,i,:]=torch.from_numpy(array_2)
kernel[3,i,:]=torch.from_numpy(array_3)
kernel[4,i,:]=torch.from_numpy(array_4)
kernel[5,i,:]=torch.from_numpy(array_5)
kernel[6,i,:]=torch.from_numpy(array_6)
kernel[7,i,:]=torch.from_numpy(array_7)
return torch.nn.Parameter(kernel,requires_grad=True)
# Calculer le poids initial de la couche convolutive add
# n, m signifie qu'il y a n * m sous-patches dans le patch d'entrée
# Par exemple, le patch d'entrée est 16 * 16, pour les patchs 4 * 4 de la première couche, n = 4, m = 4
# pour les patchs 8 * 8 de la deuxième couche, n = 2, m = 2
def kernel_add_ini(n,m):
input_canal=int(n*m)
output_canal=int(n/2)*int(m/2)
for i in range(int(n/2)):
for j in range(int(m/2)):
kernel_add=np.zeros([1,input_canal],dtype='float32')
kernel_add[0,i*2*m+j*2]=1
kernel_add[0,i*2*m+j*2+1]=1
kernel_add[0,(i*2+1)*m+j*2]=1
kernel_add[0,(i*2+1)*m+j*2+1]=1
if i==0 and j==0:
add=torch.from_numpy(kernel_add.reshape(1,input_canal,1,1))
else:
add_=torch.from_numpy(kernel_add.reshape(1,input_canal,1,1))
add=torch.cat((add,add_),0)
return torch.nn.Parameter(add,requires_grad=False)
# Calculer le poids initial de la couche convolutive shift
# shift+add Peut réaliser l'étape de l'agrégation
# Voir ci-dessus pour les paramètres n et m.
# Pour des étapes plus détaillées, veuillez consulter mon rapport de stage
def kernel_shift_ini(n,m):
input_canal=int(n*m)
output_canal=int(n*m)
kernel_shift=torch.zeros([output_canal,input_canal,3,3])
array_0=np.array([[1,0,0],[0,0,0],[0,0,0]],dtype='float32')
array_1=np.array([[0,0,1],[0,0,0],[0,0,0]],dtype='float32')
array_2=np.array([[0,0,0],[0,0,0],[1,0,0]],dtype='float32')
array_3=np.array([[0,0,0],[0,0,0],[0,0,1]],dtype='float32')
kernel_shift_0=torch.from_numpy(array_0)
kernel_shift_1=torch.from_numpy(array_1)
kernel_shift_2=torch.from_numpy(array_2)
kernel_shift_3=torch.from_numpy(array_3)
for i in range(n):
for j in range(m):
if i==0 and j==0:
kernel_shift[0,0,:]=kernel_shift_0
else:
if i%2==0 and j%2==0:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_0
if i%2==0 and j%2==1:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_1
if i%2==1 and j%2==0:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_2
if i%2==1 and j%2==1:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_3
return torch.nn.Parameter(kernel_shift,requires_grad=False)
# Trouvez le petit patch(4 * 4) dans la n ème ligne et la m ème colonne du patch d'entrée
# Ceci est utilisé pour calculer la convolution et obtenir la carte de corrélation
def get_patch(fragment,psize,n,m):
return fragment[:,:,n*psize:(n+1)*psize,m*psize:(m+1)*psize]
###################################################################################################################
class Net(nn.Module):
def __init__(self,frag_size,psize):
super(Net, self).__init__()
h_fr=frag_size
w_fr=frag_size
n=int(h_fr/psize) # n*m patches dans le patch d'entrée
m=int(w_fr/psize)
self.conv1 = nn.Conv2d(3,8,kernel_size=3,stride=1,padding=1)
# Si vous souhaitez initialiser Conv1 avec les poids de DeepMatch, exécutez la ligne suivante
# self.conv1.weight=ini()
self.Relu = nn.ReLU(inplace=True)
self.maxpooling=nn.MaxPool2d(3,stride=2, padding=1)
self.shift1=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)
self.shift1.weight=kernel_shift_ini(n,m)
self.add1 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)
self.add1.weight=kernel_add_ini(n,m)
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:# Si n=m=1，Notre réseau n'a plus besoin de plus de couches pour agréger les cartes de corrélation
self.shift2=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)
self.shift2.weight=kernel_shift_ini(n,m)
self.add2 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)
self.add2.weight=kernel_add_ini(n,m)
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:
self.shift3=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)
self.shift3.weight=kernel_shift_ini(n,m)
self.add3 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)
self.add3.weight=kernel_add_ini(n,m)
def get_descripteur(self,img,using_cuda):
# Utilisez Conv1 pour calculer le descripteur,
descripteur_img=self.Relu(self.conv1(img))
b,c,h,w=descripteur_img.shape
couche_constante=0.5*torch.ones([1,1,h,w])
if using_cuda:
couche_constante=couche_constante.cuda()
# Ajouter une couche constante pour éviter la division par 0 lors de la normalisation
descripteur_img=torch.cat((descripteur_img,couche_constante),1)
# la normalisation
descripteur_img_norm=descripteur_img/torch.norm(descripteur_img,dim=1)
return descripteur_img_norm
def forward(self,img,frag,using_cuda):
psize=4
# Utilisez Conv1 pour calculer le descripteur,
descripteur_input1=self.get_descripteur(img,using_cuda)
descripteur_input2=self.get_descripteur(frag,using_cuda)
b,c,h,w=frag.shape
n=int(h/psize)
m=int(w/psize)
#######################################
# Calculer la carte de corrélation par convolution pour les n*m patchs plus petit.
for i in range(n):
for j in range(m):
if i==0 and j==0:
map_corre=F.conv2d(descripteur_input1,get_patch(descripteur_input2,psize,i,j),padding=2)
else:
a=F.conv2d(descripteur_input1,get_patch(descripteur_input2,psize,i,j),padding=2)
map_corre=torch.cat((map_corre,a),1)
########################################
# Étape de polymérisation
map_corre=self.maxpooling(map_corre)
map_corre=self.shift1(map_corre)
map_corre=self.add1(map_corre)
#########################################
# Répétez l'étape d'agrégation jusqu'à obtenir le graphique de corrélation du patch d'entrée
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:
map_corre=self.maxpooling(map_corre)
map_corre=self.shift2(map_corre)
map_corre=self.add2(map_corre)
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:
map_corre=self.maxpooling(map_corre)
map_corre=self.shift3(map_corre)
map_corre=self.add3(map_corre)
b,c,h,w=map_corre.shape
# Normalisation de la division par maximum
map_corre=map_corre/(map_corre.max())
# Normalisation SoftMax
#map_corre=(F.softmax(map_corre.reshape(1,1,h*w,1),dim=2)).reshape(b,c,h,w)
return map_corre
# In[5]:
def run_net(net,img,frag,frag_size,using_cuda):
h,w,c=frag.shape
n=int(h/frag_size)
m=int(w/frag_size)
frag_list=[]
#####################################
# Obtenez des patchs carrés des fragments et mettez-les dans la frag_list
for i in range(n):
for j in range(m):
frag_32=frag[i*frag_size:(i+1)*frag_size,j*frag_size:(j+1)*frag_size]
if test_fragment32_32(frag_32,0.6):
frag_list.append(frag_32)
img_tensor=img2tensor(img)
######################################
if using_cuda:
img_tensor=img_tensor.cuda()
coordonnee_list=[]
#######################################
# Utilisez le réseau pour calculer les positions de tous les patchs dans frag_list[]
# Mettez le résultat du calcul dans coordonnee_list[]
for i in range(len(frag_list)):
frag_tensor=img2tensor(frag_list[i])
if using_cuda:
frag_tensor=frag_tensor.cuda()
res=net.forward(img_tensor,frag_tensor,using_cuda)
if using_cuda:
res=res.cpu()
po_h,po_w=show_coordonnee(res)
coordonnee_list.append([po_h,po_w])
h_img,w_img,c=img.shape
position=[]
for i in range(len(coordonnee_list)):
x=int(round(h_img*coordonnee_list[i][0]))
y=int(round(w_img*coordonnee_list[i][1]))
position.append([x,y])
return position
# In[10]:
if __name__=='__main__':
# La taille du patch d'entrée est de 16*16
frag_size=16
# La taille du plus petit patch dans réseau est de 4 *4 fixée
psize=4
using_cuda=True
net=Net(frag_size,psize)
# Pour chaque fresque, le nombre d'itérations est de 1000
itera=1000
if using_cuda:
net=net.cuda()
# Choisissez l'optimiseur et la fonction de coût
optimizer = torch.optim.Adam(net.parameters())
loss_func = torch.nn.MSELoss()
# Dans le processus d'apprentissage du réseau,le changement d'erreur est placé dans loss_value=[]
# et le changement de Conv1 poids est placé dans para_value[]
loss_value=[]
para_value=[]
####################################################training_net
#Les données d'entraînement sont 6 fresques
for n in range(6):
im_path="./fresque"+str(n)+".ppm"
img_training=cv2.imread(im_path)
h,w,c=img_training.shape
# Si la peinture murale est trop grande, sous-échantillonnez-la et rétrécissez-la
while h*w>(1240*900):
img_training=cv2.resize(img_training,(int(h/2),int(w/2)),interpolation=cv2.INTER_CUBIC)
h,w,c=img_training.shape
im_tensor=img2tensor(img_training)
if using_cuda:
im_tensor=im_tensor.cuda()
for i in range(itera):
# Tous les 100 cycles, enregistrez le changement de poids
if i%100==0:
para=net.conv1.weight
para=para.detach().cpu()
para_value.append(para)
frag,vt=get_training_fragment(frag_size,img_training)
frag_tensor=img2tensor(frag)
if using_cuda:
vt=vt.cuda()
frag_tensor=frag_tensor.cuda()
# Utilisez des patchs et des fresques de données d'entraînement pour faire fonctionner le réseau
frag_pred=net.forward(im_tensor,frag_tensor,using_cuda)
b,c,h,w=vt.shape
# Utilisez la fonction de coût pour calculer l'erreur
err_=loss_func(vt,frag_pred)
# Utilisez l'optimiseur pour ajuster le poids de Conv1
optimizer.zero_grad()
err_.backward(retain_graph=True)
optimizer.step()
loss_value.append(err_.tolist())
del frag_tensor,frag_pred,err_,vt
torch.cuda.empty_cache()
# In[7]:
len(loss_value)
# In[11]:
plt.plot(loss_value)
# In[12]:
file_path="./net_trainned6000"
save_net(file_path,net)

871
Frag_Match_avec_rotation.ipynb Executable file
View file

@ -0,0 +1,871 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#Tous les codes sont basés sur l'environnement suivant\n",
"#python 3.7\n",
"#opencv 3.1.0\n",
"#pytorch 1.4.0\n",
"\n",
"import torch\n",
"from torch.autograd import Variable\n",
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"import cv2\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import random\n",
"import math\n",
"import pickle\n",
"import random\n",
"from PIL import Image\n",
"import sys"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Les fonctions dans ce bloc ne sont pas utilisées par le réseau, mais certaines fonctions d'outils\n",
"\n",
"# Les fonctions de ce bloc se trouvent dans le programme d'apprentissage \n",
"# “Apprentissage_MSELoss_avec_GPU“\n",
"# et les commentaires détaillés se trouvent dans le programme d'apprentissage\n",
"\n",
"def tensor_imshow(im_tensor,cannel):\n",
" b,c,h,w=im_tensor.shape\n",
" if c==1:\n",
" plt.imshow(im_tensor.squeeze().detach().numpy())\n",
" else:\n",
" plt.imshow(im_tensor.squeeze().detach().numpy()[cannel,:])\n",
" \n",
"def get_training_fragment(frag_size,im):\n",
" h,w,c=im.shape\n",
" n=random.randint(0,int(h/frag_size)-1)\n",
" m=random.randint(0,int(w/frag_size)-1)\n",
" \n",
" shape=frag_size/4\n",
" vt_h=math.ceil((h+1)/shape)\n",
" vt_w=math.ceil((w+1)/shape)\n",
" vt=np.zeros([vt_h,vt_w])\n",
" vt_h_po=round((vt_h-1)*(n*frag_size/(h-1)+(n+1)*frag_size/(h-1))/2)\n",
" vt_w_po=round((vt_w-1)*(m*frag_size/(w-1)+(m+1)*frag_size/(w-1))/2)\n",
" vt[vt_h_po,vt_w_po]=1\n",
" vt = np.float32(vt)\n",
" vt=torch.from_numpy(vt.reshape(1,1,vt_h,vt_w))\n",
" \n",
" return im[n*frag_size:(n+1)*frag_size,m*frag_size:(m+1)*frag_size,:],vt\n",
"\n",
"def write_result_in_file(result,file_name):\n",
" n=0\n",
" with open(file_name,'w') as file:\n",
" for i in range(len(result)):\n",
" while n<result[i][0]:\n",
" s=str(n)\n",
" n=n+1\n",
" s=s+\"\\n\"\n",
" file.write(s)\n",
" s=str(result[i][0])+\" \"+str(result[i][1])+\" \"+str(result[i][2])+\" \"+str(result[i][3])\n",
" s=s+\"\\n\"\n",
" n=n+1\n",
" file.write(s)\n",
" file.close()\n",
" \n",
" \n",
"def img2tensor(im):\n",
" im=np.array(im,dtype=\"float32\")\n",
" tensor_cv = torch.from_numpy(np.transpose(im, (2, 0, 1)))\n",
" im_tensor=tensor_cv.unsqueeze(0)\n",
" return im_tensor\n",
"\n",
"def show_coordonnee(position_pred):\n",
" map_corre=position_pred.squeeze().detach().numpy()\n",
" score=sum(sum(map_corre))\n",
" h,w=map_corre.shape\n",
" max_value=map_corre.max()\n",
" coordonnee=np.where(map_corre==max_value)\n",
" return score,coordonnee[0].mean()/h,coordonnee[1].mean()/w\n",
"\n",
"def test_fragment32_32(frag,seuillage):\n",
" a=frag[:,:,0]+frag[:,:,1]+frag[:,:,2]\n",
" mask = (a == 0)\n",
" arr_new = a[mask]\n",
" if arr_new.size/a.size<=(1-seuillage):\n",
" return True\n",
" else:\n",
" return False\n",
"\n",
"def save_net(file_path,net):\n",
" pkl_file = open(file_path, 'wb')\n",
" pickle.dump(net,pkl_file)\n",
" pkl_file.close()\n",
" \n",
"def load_net(file_path): \n",
" pkl_file = open(file_path, 'rb')\n",
" net= pickle.load(pkl_file)\n",
" pkl_file.close()\n",
" return net"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Les fonctions de ce bloc sont utilisées pour construire le réseau\n",
"\n",
"# Les fonctions de ce bloc se trouvent dans le programme d'apprentissage \n",
"# “Apprentissage_MSELoss_avec_GPU“\n",
"# et les commentaires détaillés se trouvent dans le programme d'apprentissage\n",
"\n",
"def ini():\n",
" kernel=torch.zeros([8,3,3,3])\n",
" array_0=np.array([[1,2,1],[0,0,0],[-1,-2,-1]],dtype='float32')\n",
" array_1=np.array([[2,1,0],[1,0,-1],[0,-1,-2]],dtype='float32')\n",
" array_2=np.array([[1,0,-1],[2,0,-2],[1,0,-1]],dtype='float32')\n",
" array_3=np.array([[0,-1,-2],[1,0,-1],[2,1,0]],dtype='float32')\n",
" array_4=np.array([[-1,-2,-1],[0,0,0],[1,2,1]],dtype='float32')\n",
" array_5=np.array([[-2,-1,0],[-1,0,1],[0,1,2]],dtype='float32')\n",
" array_6=np.array([[-1,0,1],[-2,0,2],[-1,0,1]],dtype='float32')\n",
" array_7=np.array([[0,1,2],[-1,0,1],[-2,-1,0]],dtype='float32')\n",
" for i in range(3):\n",
" kernel[0,i,:]=torch.from_numpy(array_0)\n",
" kernel[1,i,:]=torch.from_numpy(array_1)\n",
" kernel[2,i,:]=torch.from_numpy(array_2)\n",
" kernel[3,i,:]=torch.from_numpy(array_3)\n",
" kernel[4,i,:]=torch.from_numpy(array_4)\n",
" kernel[5,i,:]=torch.from_numpy(array_5)\n",
" kernel[6,i,:]=torch.from_numpy(array_6)\n",
" kernel[7,i,:]=torch.from_numpy(array_7)\n",
" return torch.nn.Parameter(kernel,requires_grad=True) \n",
"\n",
"def kernel_add_ini(n,m):\n",
" input_canal=int(n*m)\n",
" output_canal=int(n/2)*int(m/2)\n",
" for i in range(int(n/2)):\n",
" for j in range(int(m/2)):\n",
" kernel_add=np.zeros([1,input_canal],dtype='float32')\n",
" kernel_add[0,i*2*m+j*2]=1\n",
" kernel_add[0,i*2*m+j*2+1]=1\n",
" kernel_add[0,(i*2+1)*m+j*2]=1\n",
" kernel_add[0,(i*2+1)*m+j*2+1]=1\n",
" if i==0 and j==0:\n",
" add=torch.from_numpy(kernel_add.reshape(1,input_canal,1,1))\n",
" else:\n",
" add_=torch.from_numpy(kernel_add.reshape(1,input_canal,1,1))\n",
" add=torch.cat((add,add_),0)\n",
" return torch.nn.Parameter(add,requires_grad=False) \n",
"\n",
"def kernel_shift_ini(n,m):\n",
" input_canal=int(n*m)\n",
" output_canal=int(n*m)\n",
" \n",
" kernel_shift=torch.zeros([output_canal,input_canal,3,3])\n",
" \n",
" array_0=np.array([[1,0,0],[0,0,0],[0,0,0]],dtype='float32')\n",
" array_1=np.array([[0,0,1],[0,0,0],[0,0,0]],dtype='float32')\n",
" array_2=np.array([[0,0,0],[0,0,0],[1,0,0]],dtype='float32')\n",
" array_3=np.array([[0,0,0],[0,0,0],[0,0,1]],dtype='float32')\n",
" \n",
" kernel_shift_0=torch.from_numpy(array_0)\n",
" kernel_shift_1=torch.from_numpy(array_1)\n",
" kernel_shift_2=torch.from_numpy(array_2)\n",
" kernel_shift_3=torch.from_numpy(array_3)\n",
" \n",
" \n",
" for i in range(n):\n",
" for j in range(m):\n",
" if i==0 and j==0:\n",
" kernel_shift[0,0,:]=kernel_shift_0\n",
" else:\n",
" if i%2==0 and j%2==0:\n",
" kernel_shift[i*m+j,i*m+j,:]=kernel_shift_0\n",
" if i%2==0 and j%2==1:\n",
" kernel_shift[i*m+j,i*m+j,:]=kernel_shift_1\n",
" if i%2==1 and j%2==0:\n",
" kernel_shift[i*m+j,i*m+j,:]=kernel_shift_2\n",
" if i%2==1 and j%2==1:\n",
" kernel_shift[i*m+j,i*m+j,:]=kernel_shift_3\n",
" \n",
" return torch.nn.Parameter(kernel_shift,requires_grad=False) \n",
"\n",
"def get_patch(fragment,psize,n,m):\n",
" return fragment[:,:,n*psize:(n+1)*psize,m*psize:(m+1)*psize]\n",
"\n",
"class Net(nn.Module):\n",
" def __init__(self,frag_size,psize):\n",
" super(Net, self).__init__()\n",
" \n",
" h_fr=frag_size\n",
" w_fr=frag_size\n",
" \n",
" n=int(h_fr/psize) #n*m patches\n",
" m=int(w_fr/psize)\n",
" \n",
" self.conv1 = nn.Conv2d(3,8,kernel_size=3,stride=1,padding=1)\n",
" #self.conv1.weight=ini()\n",
" self.Relu = nn.ReLU(inplace=True)\n",
" self.maxpooling=nn.MaxPool2d(3,stride=2, padding=1)\n",
" \n",
" self.shift1=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)\n",
" self.shift1.weight=kernel_shift_ini(n,m)\n",
" self.add1 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)\n",
" self.add1.weight=kernel_add_ini(n,m)\n",
" \n",
" n=int(n/2)\n",
" m=int(m/2)\n",
" if n>=2 and m>=2:\n",
" self.shift2=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)\n",
" self.shift2.weight=kernel_shift_ini(n,m)\n",
" self.add2 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)\n",
" self.add2.weight=kernel_add_ini(n,m)\n",
" \n",
" n=int(n/2)\n",
" m=int(m/2)\n",
" if n>=2 and m>=2:\n",
" self.shift3=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)\n",
" self.shift3.weight=kernel_shift_ini(n,m)\n",
" self.add3 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)\n",
" self.add3.weight=kernel_add_ini(n,m)\n",
" \n",
" \n",
" def get_descripteur(self,img,using_cuda):\n",
" descripteur_img=self.Relu(self.conv1(img))\n",
" b,c,h,w=descripteur_img.shape\n",
" couche_constante=0.5*torch.ones([1,1,h,w])\n",
" if using_cuda:\n",
" couche_constante=couche_constante.cuda()\n",
" descripteur_img=torch.cat((descripteur_img,couche_constante),1)\n",
" descripteur_img_norm=descripteur_img/torch.norm(descripteur_img,dim=1)\n",
" return descripteur_img_norm\n",
" \n",
" def forward(self,img,frag,using_cuda):\n",
" psize=4\n",
" \n",
" descripteur_input1=self.get_descripteur(img,using_cuda)\n",
" descripteur_input2=self.get_descripteur(frag,using_cuda)\n",
" \n",
" b,c,h,w=frag.shape\n",
" n=int(h/psize)\n",
" m=int(w/psize)\n",
" \n",
" for i in range(n):\n",
" for j in range(m):\n",
" if i==0 and j==0:\n",
" map_corre=F.conv2d(descripteur_input1,get_patch(descripteur_input2,psize,i,j),padding=2)\n",
" else:\n",
" a=F.conv2d(descripteur_input1,get_patch(descripteur_input2,psize,i,j),padding=2)\n",
" map_corre=torch.cat((map_corre,a),1)\n",
" #shift\n",
" map_corre=self.maxpooling(map_corre)\n",
" map_corre=self.shift1(map_corre)\n",
" map_corre=self.add1(map_corre)\n",
" \n",
" \n",
" n=int(n/2)\n",
" m=int(m/2)\n",
" if n>=2 and m>=2:\n",
" map_corre=self.maxpooling(map_corre)\n",
" map_corre=self.shift2(map_corre)\n",
" map_corre=self.add2(map_corre)\n",
" \n",
" \n",
" n=int(n/2)\n",
" m=int(m/2)\n",
" if n>=2 and m>=2:\n",
" map_corre=self.maxpooling(map_corre)\n",
" map_corre=self.shift3(map_corre)\n",
" map_corre=self.add3(map_corre)\n",
" \n",
" \n",
" b,c,h,w=map_corre.shape\n",
" map_corre=map_corre/(map_corre.max())\n",
" #map_corre=(F.softmax(map_corre.reshape(1,1,h*w,1),dim=2)).reshape(b,c,h,w)\n",
" return map_corre"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# Les fonctions de ce bloc sont utilisées pour appliquer le réseau à des fragments (pas à des patchs carrés)\n",
"\n",
"\n",
"# Cette fonction permet de sélectionner un ensemble de patchs carrés à partir d'un fragment\n",
"# Le paramètre “frag_size” fait ici référence à la taille du patch d'entrée carré (16 * 16)\n",
"# Le paramètre “seuillage” limite la proportion de pixels non noirs dans chaque patch\n",
"# Le paramètre “limite” peut limiter le nombre de correctifs trouvés dans chaque fragment\n",
"def get_patch_list(frag,frag_size,limite,seuillage):\n",
" n=0\n",
" m=0\n",
" h,w,c=frag.shape\n",
" patch_list=[]\n",
" position_list=[]\n",
" for i in range(4):\n",
" if len(patch_list)>limite and limite!=0:\n",
" break\n",
" for j in range(4):\n",
" if len(patch_list)>limite and limite!=0:\n",
" break\n",
" n_offset=i*4 # n offset\n",
" m_offset=j*4 # m offset\n",
" n=0\n",
" while n+frag_size+n_offset<h:\n",
" m=0\n",
" while m+frag_size+m_offset<w:\n",
" patch=frag[n+n_offset:n+frag_size+n_offset,m+m_offset:m+frag_size+m_offset,:]\n",
" if test_fragment32_32(patch,seuillage):\n",
" patch_list.append(patch)\n",
" position_list.append([int((n+frag_size/2)+n_offset),int((m+frag_size/2)+m_offset)])\n",
" m=m+frag_size\n",
" n=n+frag_size\n",
" return patch_list,position_list\n",
"\n",
"# Entrez du fragment et de la fresque, exécutez le réseau\n",
"def run_net_v3(net,img,frag,frag_size,limite,seuillage,using_cuda,rotation):\n",
" Img=Image.fromarray(frag)\n",
" frag=np.array(Img.rotate(rotation))\n",
" img_tensor=img2tensor(img)\n",
" \n",
" # la collection de patchs carrée dans le fragement \"sont frag_list[]\"\n",
" # La position de leur centre dans la fragment sont \"position_frag[]\"\n",
" frag_list,position_frag=get_patch_list(frag,frag_size,limite,seuillage)\n",
" if using_cuda:\n",
" img_tensor=img_tensor.cuda()\n",
" \n",
" score_list=[]\n",
" coordonnee_list=[]\n",
" \n",
" # Pour chaque patch carré dans la collection, effectuez un calcul en réseau de leur position\n",
" # Le résultat est placé en \"coordonnee_list[]\"\n",
" # \"score_list[]\" pas utile dans notre programme\n",
" for i in range(len(frag_list)):\n",
" frag_tensor=img2tensor(frag_list[i])\n",
" if using_cuda:\n",
" frag_tensor=frag_tensor.cuda()\n",
" res=net.forward(img_tensor,frag_tensor,using_cuda)\n",
" if using_cuda:\n",
" res=res.cpu()\n",
" score,po_h,po_w=show_coordonnee(res)\n",
" coordonnee_list.append([po_h,po_w])\n",
" score_list.append(score)\n",
" h_img,w_img,c=img.shape\n",
" position=[]\n",
" \n",
" # Mettez les paires correspondante en \"position[]\"\n",
" # [x,y,x',y']\n",
" # La position (x,y) dans le fragment correspond à la position (x',y') dans la fresque\n",
" for i in range(len(coordonnee_list)):\n",
" x0=position_frag[i][0]\n",
" y0=position_frag[i][1]\n",
" x1=int(round(h_img*coordonnee_list[i][0]))\n",
" y1=int(round(w_img*coordonnee_list[i][1]))\n",
" position.append([x0,y0,x1,y1])\n",
" return score_list,position"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"# Cette partie du code consiste à implémenter l'algorithme RANSAC amélioré\n",
"\n",
"# Ecrire le point sous forme [x,y,1]T,\n",
"# Utilisé pour construire l'équation de la matrice de transformation\n",
"def creer_point(x,y):\n",
" p=np.zeros((3,1))\n",
" p[0][0]=x\n",
" p[1][0]=y\n",
" p[2][0]=1\n",
" return p\n",
"\n",
"# Sélectionnez aléatoirement n points sans duplication à partir de M points\n",
"def selectionner_points(n,M):\n",
" table=[]\n",
" for i in range(M):\n",
" table.append(i)\n",
" result=[]\n",
" for i in range(n):\n",
" index=random.randint(0,M-i-1)\n",
" result.append(table[index])\n",
" table[index]=table[M-1-i]\n",
" return result\n",
"\n",
"# Selon la matrice de transformation affine, calculer la position centrale transformée et l'angle de rotation\n",
"def position_rotation(h,centre_frag):\n",
" centre=h@centre_frag\n",
" cos_rot=(h[0][0]+h[1][1])/2\n",
" sin_rot=(h[1][0]-h[0][1])/2\n",
" tan_rot=sin_rot/(cos_rot+0.0000001)\n",
" if cos_rot>0:\n",
" rot_frag=math.atan(tan_rot)*(180/pi)\n",
" else:\n",
" rot_frag=math.atan(tan_rot)*(180/pi)+180\n",
" rot_frag=-rot_frag\n",
" if rot_frag>0:\n",
" rot_frag-=360\n",
" return centre[0][0],centre[1][0],rot_frag\n",
"\n",
"# Vérifiez les résultats de Ransac en avec des changements de distance euclidienne\n",
"def test_frag(inline,frag,fres):\n",
" itera=10\n",
" frag_inline=[]\n",
" fres_inline=[]\n",
" # Metter les coordonnées du point inline dans \"frag_inline[]\",et \"fres_inline[]\"\n",
" for i in range(np.size(inline,0)):\n",
" if inline[i]==1:\n",
" frag_inline.append([frag[i][0],frag[i][1]])\n",
" fres_inline.append([fres[i][0],fres[i][1]])\n",
" p=[]\n",
" \n",
" # Faites une boucle dix fois, \n",
" # sélectionnez à chaque fois deux paires correspondantes inline \n",
" # calculer le changement de leur distance euclidienne\n",
" for i in range(itera):\n",
" point_test=selectionner_points(2,np.size(frag_inline,0))\n",
" diff_x_frag=frag_inline[point_test[1]][0]-frag_inline[point_test[0]][0]\n",
" diff_y_frag=frag_inline[point_test[1]][1]-frag_inline[point_test[0]][1]\n",
" diff_frag=sqrt(pow(diff_x_frag,2)+pow(diff_y_frag,2))\n",
" \n",
" diff_x_fres=fres_inline[point_test[1]][0]-fres_inline[point_test[0]][0]\n",
" diff_y_fres=fres_inline[point_test[1]][1]-fres_inline[point_test[0]][1]\n",
" diff_fres=sqrt(pow(diff_x_fres,2)+pow(diff_y_fres,2))\n",
" if diff_frag !=0:\n",
" fsf=diff_fres/diff_frag\n",
" p.append([fsf])\n",
" result=np.mean(p)\n",
" return result\n",
"\n",
"def frag_match(frag,img,position):\n",
" \n",
" frag_size=frag.shape\n",
" centre_frag=creer_point(frag_size[0]/2,frag_size[1]/2)\n",
" \n",
" retained_matches = []\n",
" frag=[]\n",
" fres=[]\n",
" \n",
" for i in range(len(position)):\n",
" frag.append([float(position[i][0]),float(position[i][1])])\n",
" fres.append([float(position[i][2]),float(position[i][3])])\n",
" \n",
" if np.size(frag)>0:\n",
" # Calculer la matrice de transformation affine à l'aide de la méthode Ransac\n",
" h,inline=cv2.estimateAffinePartial2D(np.array(frag),np.array(fres))\n",
" # Si “h” n'est pas sous la forme de matrice 2 * 3, la matrice de transformation affine n'est pas trouvée\n",
" if np.size(h)!=6:\n",
" return ([-1])\n",
" else:\n",
" x,y,rot=position_rotation(h,centre_frag)\n",
" pourcenttage=sum(inline)/np.size(frag,0)\n",
" # Le nombre de points inline doit être supérieur à un certain nombre\n",
" if sum(inline)>3:\n",
" p=test_frag(inline,frag,fres)\n",
" # La distance euclidienne entre les points correspondants ne doit pas trop changer, \n",
" # sinon cela prouve que le résultat de Ransac est incorrect\n",
" # ici,le changement de la distance euclidienne sont entre 0.7 et 1.3\n",
" if abs(p-1)<0.3:\n",
" # Ce n'est qu'alors que Ransac renvoie le résultat correct\n",
" return([round(y),round(x),round(rot,3)])\n",
" else:\n",
" return ([-2])\n",
" else:\n",
" return ([-3])\n",
" else:\n",
" return ([-4]) "
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"if __name__==\"__main__\":\n",
" \n",
" frag_size=16\n",
" using_cuda=True\n",
" net=load_net(\"./net_trainned6000\")\n",
" img_test=cv2.imread(\"./fresque0.ppm\")\n",
" \n",
" result=[]\n",
" for n in range(315):\n",
" if n<10:\n",
" frag_test=cv2.imread(\"./frag_eroded0/frag_eroded_000\"+str(n)+\".ppm\")\n",
" elif n<100:\n",
" frag_test=cv2.imread(\"./frag_eroded0/frag_eroded_00\"+str(n)+\".ppm\")\n",
" else:\n",
" frag_test=cv2.imread(\"./frag_eroded0/frag_eroded_0\"+str(n)+\".ppm\")\n",
" \n",
" # Faites pivoter les pièces de 20 degrés à chaque fois pour correspondre, répétez 18 fois\n",
" for i in range(18):\n",
" rotation=20*i\n",
" score_list,position=run_net_v3(net,img_test,frag_test,frag_size,60,0.7,using_cuda,rotation)\n",
" frag_position=frag_match(frag_test,img_test,position)\n",
" # Lorsque Ransac obtient le bon résultat, sortez de la boucle\n",
" if len(frag_position)==3:\n",
" rotation_base=i*20\n",
" break\n",
" # Enregistrez les fragments correctement localisés dans \"result[]\"\n",
" if len(frag_position)==3:\n",
" frag_position[2]=rotation_base-360-frag_position[2]\n",
" if frag_position[2]>0:\n",
" frag_position[2]=frag_position[2]-360\n",
" result.append([n,frag_position[0],frag_position[1],round(frag_position[2],3)])\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[0, 520.0, 575.0, -356.388],\n",
" [1, 535.0, 460.0, -113.454],\n",
" [2, 971.0, 270.0, -40.966],\n",
" [3, 1641.0, 650.0, -119.543],\n",
" [4, 1349.0, 68.0, -336.356],\n",
" [5, 1509.0, 192.0, -298.759],\n",
" [6, 107.0, 521.0, -74.179],\n",
" [7, 420.0, 440.0, -174.266],\n",
" [8, 287.0, 533.0, -299.677],\n",
" [9, 1518.0, 167.0, -290.164],\n",
" [10, 231.0, 429.0, -180.983],\n",
" [11, 666.0, 483.0, -230.948],\n",
" [12, 855.0, 104.0, -346.884],\n",
" [13, 1267.0, 87.0, -305.562],\n",
" [14, 16.0, 705.0, -30.087],\n",
" [15, 924.0, 120.0, -146.41],\n",
" [16, 657.0, 372.0, -175.323],\n",
" [17, 1409.0, 528.0, -329.829],\n",
" [18, 618.0, 427.0, -350.062],\n",
" [19, 631.0, 269.0, -87.332],\n",
" [20, 1345.0, 579.0, -320.597],\n",
" [21, 1670.0, 139.0, -282.108],\n",
" [22, 1310.0, 4.0, -180.0],\n",
" [23, 1418.0, 29.0, -112.925],\n",
" [24, 874.0, 496.0, -312.046],\n",
" [25, 812.0, 537.0, -4.393],\n",
" [26, 47.0, 728.0, -82.997],\n",
" [27, 1411.0, 200.0, -324.46],\n",
" [28, 767.0, 595.0, -339.734],\n",
" [29, 361.0, 434.0, -349.088],\n",
" [30, 1264.0, 732.0, -211.149],\n",
" [31, 958.0, 738.0, -356.008],\n",
" [32, 1307.0, 679.0, -145.032],\n",
" [33, 704.0, 553.0, -197.736],\n",
" [34, 867.0, 344.0, -355.599],\n",
" [35, 1702.0, 164.0, -315.301],\n",
" [36, 1483.0, 307.0, -330.954],\n",
" [37, 1365.0, 661.0, -158.589],\n",
" [38, 35.0, 623.0, -301.166],\n",
" [39, 968.0, 40.0, -355.307],\n",
" [40, 137.0, 650.0, -127.38],\n",
" [41, 1527.0, 239.0, -113.919],\n",
" [42, 1176.0, 736.0, -218.247],\n",
" [43, 466.0, 676.0, -139.007],\n",
" [44, 297.0, 659.0, -22.509],\n",
" [45, 1075.0, 363.0, -1.866],\n",
" [46, 973.0, 658.0, -118.442],\n",
" [47, 658.0, 589.0, -134.967],\n",
" [48, 1438.0, 245.0, -63.213],\n",
" [49, 1019.0, 381.0, -4.052],\n",
" [50, 898.0, 586.0, -320.709],\n",
" [51, 738.0, 258.0, -298.33],\n",
" [52, 1668.0, 167.0, -257.834],\n",
" [53, 306.0, 201.0, -304.816],\n",
" [54, 129.0, 353.0, -123.722],\n",
" [55, 1612.0, 527.0, -201.46],\n",
" [56, 1406.0, 400.0, -132.928],\n",
" [57, 1223.0, 629.0, -243.388],\n",
" [58, 1603.0, 770.0, -223.688],\n",
" [59, 1451.0, 323.0, -4.008],\n",
" [60, 1262.0, -8.0, -143.496],\n",
" [61, 1409.0, 358.0, -244.745],\n",
" [62, 426.0, 567.0, -107.651],\n",
" [63, 1093.0, 536.0, -11.543],\n",
" [64, 1570.0, 763.0, -340.0],\n",
" [65, 599.0, 29.0, -352.066],\n",
" [66, 38.0, 522.0, -237.017],\n",
" [67, 1076.0, 29.0, -152.794],\n",
" [68, 1629.0, 79.0, -70.396],\n",
" [69, 1464.0, 311.0, -306.565],\n",
" [70, 1595.0, 260.0, -53.364],\n",
" [71, 1343.0, 273.0, -256.237],\n",
" [72, 1074.0, 236.0, -1.801],\n",
" [73, 132.0, 35.0, -160.03],\n",
" [74, 1627.0, 762.0, -235.274],\n",
" [75, 713.0, 361.0, -136.338],\n",
" [76, 1485.0, 85.0, -90.974],\n",
" [77, 1243.0, 153.0, -268.034],\n",
" [78, 1026.0, 511.0, -118.767],\n",
" [79, 240.0, 181.0, -51.205],\n",
" [80, 1085.0, 680.0, -53.483],\n",
" [81, 73.0, 212.0, -299.054],\n",
" [82, 1237.0, 389.0, -306.557],\n",
" [83, 1269.0, 87.0, -330.538],\n",
" [84, 29.0, 175.0, -298.41],\n",
" [85, 982.0, 97.0, -80.0],\n",
" [86, 1487.0, 276.0, -211.009],\n",
" [87, 1226.0, 114.0, -321.565],\n",
" [88, 60.0, 317.0, -127.895],\n",
" [89, 1351.0, 285.0, -322.595],\n",
" [90, 233.0, 33.0, -144.993],\n",
" [91, 807.0, 211.0, -1.747],\n",
" [92, 997.0, 558.0, -326.669],\n",
" [93, 1682.0, 283.0, -312.023],\n",
" [94, 1178.0, 691.0, -242.927],\n",
" [95, 1116.0, 487.0, -288.69],\n",
" [96, 952.0, 14.0, -275.225],\n",
" [97, 140.0, 765.0, -206.9],\n",
" [98, 772.0, 81.0, -112.039],\n",
" [99, 640.0, 682.0, -57.917],\n",
" [100, 121.0, 757.0, -231.821],\n",
" [101, 1484.0, 218.0, -15.255],\n",
" [102, 1304.0, 164.0, -273.435],\n",
" [103, 862.0, 192.0, -303.177],\n",
" [104, 258.0, 766.0, -257.769],\n",
" [105, 540.0, 714.0, -183.176],\n",
" [106, 1283.0, 264.0, -330.905],\n",
" [107, 507.0, 196.0, -333.629],\n",
" [108, 1428.0, 438.0, -209.806],\n",
" [109, 391.0, 739.0, -243.391],\n",
" [110, 250.0, 640.0, -287.596],\n",
" [111, 704.0, 102.0, -78.376],\n",
" [112, 1060.0, 227.0, -300.726],\n",
" [113, 1509.0, 302.0, -318.749],\n",
" [114, 895.0, 662.0, -199.664],\n",
" [115, 1453.0, 254.0, -260.0],\n",
" [116, 1058.0, 199.0, -218.275],\n",
" [117, 1416.0, 779.0, 0.0],\n",
" [118, 1054.0, 740.0, -197.173],\n",
" [119, 1352.0, 393.0, -309.992],\n",
" [120, 1273.0, 585.0, -334.957],\n",
" [121, 952.0, 566.0, -193.436],\n",
" [122, 1132.0, 456.0, -25.393],\n",
" [123, 598.0, 179.0, -308.525],\n",
" [124, 1270.0, 15.0, -260.0],\n",
" [125, 763.0, 462.0, -241.979],\n",
" [126, 1515.0, 307.0, -284.007],\n",
" [127, 1582.0, 608.0, -175.422],\n",
" [128, 388.0, 536.0, -166.952],\n",
" [129, 426.0, 667.0, -84.451],\n",
" [130, 1505.0, 18.0, -192.572],\n",
" [131, 976.0, 440.0, -260.194],\n",
" [132, 1467.0, 655.0, -345.072],\n",
" [133, 1085.0, 388.0, -323.091],\n",
" [134, 1189.0, 514.0, -99.219],\n",
" [135, 232.0, 751.0, -360.0],\n",
" [136, 1336.0, 91.0, -132.694],\n",
" [137, 765.0, 173.0, -54.653],\n",
" [138, 1451.0, 421.0, -291.464],\n",
" [139, 920.0, 370.0, -271.035],\n",
" [140, 314.0, 739.0, -302.917],\n",
" [141, 1225.0, 213.0, -281.565],\n",
" [143, 160.0, 716.0, -238.299],\n",
" [144, 503.0, 31.0, -348.257],\n",
" [145, 1159.0, 423.0, -94.766],\n",
" [146, 131.0, 716.0, -27.957],\n",
" [147, 20.0, 683.0, -230.611],\n",
" [148, 237.0, 756.0, -164.897],\n",
" [149, 1596.0, 19.0, -285.437],\n",
" [150, 238.0, 737.0, -17.033],\n",
" [151, 354.0, 151.0, -100.638],\n",
" [152, 887.0, 257.0, -318.435],\n",
" [153, 541.0, 142.0, -151.453],\n",
" [154, 1177.0, 82.0, -275.589],\n",
" [155, 1526.0, 594.0, -340.0],\n",
" [156, 1454.0, 307.0, -305.964],\n",
" [157, 327.0, 150.0, -161.526],\n",
" [158, 1288.0, 199.0, -314.289],\n",
" [159, 649.0, 179.0, -333.417],\n",
" [160, 1413.0, 255.0, -283.537],\n",
" [161, 1543.0, 61.0, -307.416],\n",
" [162, 1190.0, 144.0, -226.857],\n",
" [163, 587.0, 104.0, -151.213],\n",
" [164, 1320.0, 602.0, -315.852],\n",
" [165, 627.0, 104.0, -320.252],\n",
" [166, 1474.0, 413.0, -233.361],\n",
" [167, 699.0, 176.0, -178.052],\n",
" [168, 1024.0, 341.0, -259.2],\n",
" [169, 1701.0, 755.0, -304.039],\n",
" [170, 1684.0, 210.0, -244.828],\n",
" [171, 1330.0, 290.0, -21.864],\n",
" [172, 1053.0, 139.0, -324.51],\n",
" [173, 1643.0, 428.0, -331.469],\n",
" [174, 319.0, 542.0, -205.964],\n",
" [175, 1045.0, 91.0, -3.533],\n",
" [176, 828.0, 695.0, -295.602],\n",
" [177, 1631.0, 287.0, -132.225],\n",
" [178, 361.0, 677.0, -142.992],\n",
" [179, 1674.0, 350.0, -227.628],\n",
" [180, 1412.0, 764.0, -350.194],\n",
" [181, 845.0, 19.0, -27.206],\n",
" [183, 1239.0, 192.0, -317.673],\n",
" [184, 320.0, 39.0, -157.845],\n",
" [185, 1387.0, 749.0, -46.487],\n",
" [186, 166.0, 589.0, -211.473],\n",
" [187, 1339.0, 122.0, -258.435],\n",
" [188, 1216.0, 235.0, -163.194],\n",
" [189, 1677.0, 696.0, -275.899],\n",
" [190, 158.0, 762.0, -327.275],\n",
" [191, 1078.0, 254.0, -226.278],\n",
" [192, 468.0, 761.0, -280.0],\n",
" [193, 439.0, 44.0, -182.45],\n",
" [194, 161.0, 541.0, -354.612],\n",
" [195, 972.0, 502.0, -335.421],\n",
" [196, 427.0, 192.0, -300.872],\n",
" [197, 17.0, 358.0, -137.835],\n",
" [198, 210.0, 580.0, -7.095],\n",
" [199, 259.0, 601.0, -228.13],\n",
" [200, 583.0, 736.0, -154.988],\n",
" [201, 216.0, 751.0, -302.426],\n",
" [202, 826.0, 46.0, -162.036],\n",
" [203, 1592.0, 382.0, -344.745],\n",
" [204, 1533.0, 110.0, -332.592],\n",
" [205, 159.0, 761.0, -21.87],\n",
" [206, 1219.0, 473.0, -297.199],\n",
" [207, 1697.0, 711.0, -103.887],\n",
" [208, 1449.0, 289.0, -247.773],\n",
" [209, 1694.0, 749.0, -48.106],\n",
" [210, 842.0, 613.0, -235.221],\n",
" [211, 1046.0, 294.0, -134.05],\n",
" [212, 1696.0, 763.0, -258.435],\n",
" [213, 350.0, 83.0, -189.227],\n",
" [214, 1262.0, 482.0, -347.386],\n",
" [215, 310.0, 321.0, -211.399],\n",
" [216, 744.0, 22.0, -268.647],\n",
" [218, 1353.0, 732.0, -72.057],\n",
" [219, 1418.0, 770.0, -340.0],\n",
" [220, 496.0, 718.0, -20.0],\n",
" [221, 477.0, 149.0, -277.479],\n",
" [222, 1547.0, 87.0, -325.069],\n",
" [223, 1087.0, 345.0, -3.805],\n",
" [224, 259.0, 78.0, -19.36],\n",
" [225, 1530.0, 512.0, -276.062],\n",
" [226, 132.0, 730.0, -360.0],\n",
" [227, 944.0, 471.0, -170.0],\n",
" [228, 1245.0, 256.0, -155.672],\n",
" [229, 1615.0, 354.0, -81.565],\n",
" [230, 177.0, 72.0, -198.674],\n",
" [231, 1637.0, 470.0, -350.62],\n",
" [232, 540.0, 644.0, -4.911],\n",
" [233, 624.0, 625.0, -127.127],\n",
" [234, 420.0, 15.0, -187.058],\n",
" [235, 884.0, 751.0, -288.649],\n",
" [236, 267.0, 776.0, -339.146],\n",
" [237, 1129.0, 87.0, -10.008],\n",
" [238, 1700.0, 713.0, -240.764],\n",
" [239, 286.0, 283.0, -148.653],\n",
" [240, 679.0, 730.0, -336.762],\n",
" [241, 1129.0, 106.0, -326.244],\n",
" [242, 1292.0, 200.0, -203.69],\n",
" [243, 1693.0, 570.0, -140.0],\n",
" [244, 1529.0, 114.0, -341.565],\n",
" [245, 158.0, 759.0, -356.87],\n",
" [246, 1116.0, 563.0, -242.203],\n",
" [247, 283.0, 129.0, -309.725],\n",
" [248, 1597.0, 294.0, -312.875],\n",
" [249, 1709.0, 762.0, -273.435],\n",
" [250, 1377.0, 302.0, -314.179],\n",
" [251, 323.0, 364.0, -6.183],\n",
" [252, 1316.0, 485.0, -280.0],\n",
" [253, 962.0, 16.0, -280.0],\n",
" [254, 1198.0, 573.0, -11.792],\n",
" [255, 276.0, 384.0, -279.393],\n",
" [256, 1684.0, 734.0, -104.219],\n",
" [257, 1447.0, 333.0, -280.5],\n",
" [258, 999.0, 256.0, -227.883],\n",
" [259, 1014.0, 413.0, -325.59],\n",
" [260, 141.0, 724.0, -216.565],\n",
" [261, 1552.0, 545.0, -255.848],\n",
" [262, 292.0, 13.0, -191.87],\n",
" [263, 573.0, 681.0, -79.779],\n",
" [264, 1433.0, 740.0, -149.733],\n",
" [265, 138.0, 726.0, -311.027],\n",
" [266, 1617.0, 762.0, -327.995],\n",
" [267, 170.0, 141.0, -335.639],\n",
" [268, 1282.0, 441.0, -324.876],\n",
" [269, 322.0, 255.0, -143.393],\n",
" [270, 100.0, 762.0, -56.809],\n",
" [271, 1249.0, 533.0, -349.403],\n",
" [272, 1097.0, 584.0, -213.29],\n",
" [274, 1697.0, 712.0, -360.0],\n",
" [275, 399.0, 148.0, -176.849],\n",
" [276, 56.0, 452.0, -155.208],\n",
" [277, 166.0, 16.0, -336.461],\n",
" [278, 58.0, 406.0, -233.24],\n",
" [279, 1552.0, 79.0, -69.146],\n",
" [280, 746.0, 134.0, -259.441],\n",
" [281, 123.0, 106.0, -103.672],\n",
" [282, 160.0, 758.0, -64.289],\n",
" [283, 1454.0, 323.0, -100.71],\n",
" [284, 220.0, 98.0, -135.362],\n",
" [285, 1173.0, 234.0, -105.515],\n",
" [286, 1238.0, 576.0, -360.0],\n",
" [287, 383.0, 194.0, -259.057],\n",
" [288, 1693.0, 147.0, -322.49],\n",
" [289, 286.0, 351.0, -360.0],\n",
" [290, 648.0, 734.0, -27.933],\n",
" [292, 160.0, 492.0, -111.87],\n",
" [293, 1105.0, 621.0, -115.047],\n",
" [294, 1108.0, 241.0, -227.684],\n",
" [295, 1212.0, 278.0, -340.0],\n",
" [296, 844.0, 756.0, -338.456],\n",
" [298, 1693.0, 111.0, -278.435],\n",
" [299, 1530.0, 563.0, -335.376],\n",
" [301, 364.0, 316.0, -360.0],\n",
" [303, 1690.0, 15.0, -3.881],\n",
" [304, 1170.0, 179.0, -151.87],\n",
" [305, 1408.0, 331.0, -11.189],\n",
" [307, 1654.0, 12.0, -280.0],\n",
" [308, 1180.0, 207.0, -80.017],\n",
" [309, 86.0, 403.0, -185.0],\n",
" [313, 281.0, 317.0, -120.0]]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "py37",
"language": "python",
"name": "py37"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

515
Frag_Match_avec_rotation.py Normal file
View file

@ -0,0 +1,515 @@
#!/usr/bin/env python
# coding: utf-8
# In[1]:
#Tous les codes sont basés sur l'environnement suivant
#python 3.7
#opencv 3.1.0
#pytorch 1.4.0
import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import cv2
import matplotlib.pyplot as plt
import numpy as np
import random
import math
import pickle
import random
from PIL import Image
import sys
# In[2]:
# Les fonctions dans ce bloc ne sont pas utilisées par le réseau, mais certaines fonctions d'outils
# Les fonctions de ce bloc se trouvent dans le programme d'apprentissage
# “Apprentissage_MSELoss_avec_GPU“
# et les commentaires détaillés se trouvent dans le programme d'apprentissage
def tensor_imshow(im_tensor,cannel):
b,c,h,w=im_tensor.shape
if c==1:
plt.imshow(im_tensor.squeeze().detach().numpy())
else:
plt.imshow(im_tensor.squeeze().detach().numpy()[cannel,:])
def get_training_fragment(frag_size,im):
h,w,c=im.shape
n=random.randint(0,int(h/frag_size)-1)
m=random.randint(0,int(w/frag_size)-1)
shape=frag_size/4
vt_h=math.ceil((h+1)/shape)
vt_w=math.ceil((w+1)/shape)
vt=np.zeros([vt_h,vt_w])
vt_h_po=round((vt_h-1)*(n*frag_size/(h-1)+(n+1)*frag_size/(h-1))/2)
vt_w_po=round((vt_w-1)*(m*frag_size/(w-1)+(m+1)*frag_size/(w-1))/2)
vt[vt_h_po,vt_w_po]=1
vt = np.float32(vt)
vt=torch.from_numpy(vt.reshape(1,1,vt_h,vt_w))
return im[n*frag_size:(n+1)*frag_size,m*frag_size:(m+1)*frag_size,:],vt
def write_result_in_file(result,file_name):
n=0
with open(file_name,'w') as file:
for i in range(len(result)):
while n<result[i][0]:
s=str(n)
n=n+1
s=s+"\n"
file.write(s)
s=str(result[i][0])+" "+str(result[i][1])+" "+str(result[i][2])+" "+str(result[i][3])
s=s+"\n"
n=n+1
file.write(s)
file.close()
def img2tensor(im):
im=np.array(im,dtype="float32")
tensor_cv = torch.from_numpy(np.transpose(im, (2, 0, 1)))
im_tensor=tensor_cv.unsqueeze(0)
return im_tensor
def show_coordonnee(position_pred):
map_corre=position_pred.squeeze().detach().numpy()
score=sum(sum(map_corre))
h,w=map_corre.shape
max_value=map_corre.max()
coordonnee=np.where(map_corre==max_value)
return score,coordonnee[0].mean()/h,coordonnee[1].mean()/w
def test_fragment32_32(frag,seuillage):
a=frag[:,:,0]+frag[:,:,1]+frag[:,:,2]
mask = (a == 0)
arr_new = a[mask]
if arr_new.size/a.size<=(1-seuillage):
return True
else:
return False
def save_net(file_path,net):
pkl_file = open(file_path, 'wb')
pickle.dump(net,pkl_file)
pkl_file.close()
def load_net(file_path):
pkl_file = open(file_path, 'rb')
net= pickle.load(pkl_file)
pkl_file.close()
return net
# In[3]:
# Les fonctions de ce bloc sont utilisées pour construire le réseau
# Les fonctions de ce bloc se trouvent dans le programme d'apprentissage
# “Apprentissage_MSELoss_avec_GPU“
# et les commentaires détaillés se trouvent dans le programme d'apprentissage
def ini():
kernel=torch.zeros([8,3,3,3])
array_0=np.array([[1,2,1],[0,0,0],[-1,-2,-1]],dtype='float32')
array_1=np.array([[2,1,0],[1,0,-1],[0,-1,-2]],dtype='float32')
array_2=np.array([[1,0,-1],[2,0,-2],[1,0,-1]],dtype='float32')
array_3=np.array([[0,-1,-2],[1,0,-1],[2,1,0]],dtype='float32')
array_4=np.array([[-1,-2,-1],[0,0,0],[1,2,1]],dtype='float32')
array_5=np.array([[-2,-1,0],[-1,0,1],[0,1,2]],dtype='float32')
array_6=np.array([[-1,0,1],[-2,0,2],[-1,0,1]],dtype='float32')
array_7=np.array([[0,1,2],[-1,0,1],[-2,-1,0]],dtype='float32')
for i in range(3):
kernel[0,i,:]=torch.from_numpy(array_0)
kernel[1,i,:]=torch.from_numpy(array_1)
kernel[2,i,:]=torch.from_numpy(array_2)
kernel[3,i,:]=torch.from_numpy(array_3)
kernel[4,i,:]=torch.from_numpy(array_4)
kernel[5,i,:]=torch.from_numpy(array_5)
kernel[6,i,:]=torch.from_numpy(array_6)
kernel[7,i,:]=torch.from_numpy(array_7)
return torch.nn.Parameter(kernel,requires_grad=True)
def kernel_add_ini(n,m):
input_canal=int(n*m)
output_canal=int(n/2)*int(m/2)
for i in range(int(n/2)):
for j in range(int(m/2)):
kernel_add=np.zeros([1,input_canal],dtype='float32')
kernel_add[0,i*2*m+j*2]=1
kernel_add[0,i*2*m+j*2+1]=1
kernel_add[0,(i*2+1)*m+j*2]=1
kernel_add[0,(i*2+1)*m+j*2+1]=1
if i==0 and j==0:
add=torch.from_numpy(kernel_add.reshape(1,input_canal,1,1))
else:
add_=torch.from_numpy(kernel_add.reshape(1,input_canal,1,1))
add=torch.cat((add,add_),0)
return torch.nn.Parameter(add,requires_grad=False)
def kernel_shift_ini(n,m):
input_canal=int(n*m)
output_canal=int(n*m)
kernel_shift=torch.zeros([output_canal,input_canal,3,3])
array_0=np.array([[1,0,0],[0,0,0],[0,0,0]],dtype='float32')
array_1=np.array([[0,0,1],[0,0,0],[0,0,0]],dtype='float32')
array_2=np.array([[0,0,0],[0,0,0],[1,0,0]],dtype='float32')
array_3=np.array([[0,0,0],[0,0,0],[0,0,1]],dtype='float32')
kernel_shift_0=torch.from_numpy(array_0)
kernel_shift_1=torch.from_numpy(array_1)
kernel_shift_2=torch.from_numpy(array_2)
kernel_shift_3=torch.from_numpy(array_3)
for i in range(n):
for j in range(m):
if i==0 and j==0:
kernel_shift[0,0,:]=kernel_shift_0
else:
if i%2==0 and j%2==0:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_0
if i%2==0 and j%2==1:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_1
if i%2==1 and j%2==0:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_2
if i%2==1 and j%2==1:
kernel_shift[i*m+j,i*m+j,:]=kernel_shift_3
return torch.nn.Parameter(kernel_shift,requires_grad=False)
def get_patch(fragment,psize,n,m):
return fragment[:,:,n*psize:(n+1)*psize,m*psize:(m+1)*psize]
class Net(nn.Module):
def __init__(self,frag_size,psize):
super(Net, self).__init__()
h_fr=frag_size
w_fr=frag_size
n=int(h_fr/psize) #n*m patches
m=int(w_fr/psize)
self.conv1 = nn.Conv2d(3,8,kernel_size=3,stride=1,padding=1)
#self.conv1.weight=ini()
self.Relu = nn.ReLU(inplace=True)
self.maxpooling=nn.MaxPool2d(3,stride=2, padding=1)
self.shift1=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)
self.shift1.weight=kernel_shift_ini(n,m)
self.add1 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)
self.add1.weight=kernel_add_ini(n,m)
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:
self.shift2=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)
self.shift2.weight=kernel_shift_ini(n,m)
self.add2 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)
self.add2.weight=kernel_add_ini(n,m)
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:
self.shift3=nn.Conv2d(n*m,n*m,kernel_size=3,stride=1,padding=1)
self.shift3.weight=kernel_shift_ini(n,m)
self.add3 = nn.Conv2d(n*m,int(n/2)*int(m/2),kernel_size=1,stride=1,padding=0)
self.add3.weight=kernel_add_ini(n,m)
def get_descripteur(self,img,using_cuda):
descripteur_img=self.Relu(self.conv1(img))
b,c,h,w=descripteur_img.shape
couche_constante=0.5*torch.ones([1,1,h,w])
if using_cuda:
couche_constante=couche_constante.cuda()
descripteur_img=torch.cat((descripteur_img,couche_constante),1)
descripteur_img_norm=descripteur_img/torch.norm(descripteur_img,dim=1)
return descripteur_img_norm
def forward(self,img,frag,using_cuda):
psize=4
descripteur_input1=self.get_descripteur(img,using_cuda)
descripteur_input2=self.get_descripteur(frag,using_cuda)
b,c,h,w=frag.shape
n=int(h/psize)
m=int(w/psize)
for i in range(n):
for j in range(m):
if i==0 and j==0:
map_corre=F.conv2d(descripteur_input1,get_patch(descripteur_input2,psize,i,j),padding=2)
else:
a=F.conv2d(descripteur_input1,get_patch(descripteur_input2,psize,i,j),padding=2)
map_corre=torch.cat((map_corre,a),1)
#shift
map_corre=self.maxpooling(map_corre)
map_corre=self.shift1(map_corre)
map_corre=self.add1(map_corre)
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:
map_corre=self.maxpooling(map_corre)
map_corre=self.shift2(map_corre)
map_corre=self.add2(map_corre)
n=int(n/2)
m=int(m/2)
if n>=2 and m>=2:
map_corre=self.maxpooling(map_corre)
map_corre=self.shift3(map_corre)
map_corre=self.add3(map_corre)
b,c,h,w=map_corre.shape
map_corre=map_corre/(map_corre.max())
#map_corre=(F.softmax(map_corre.reshape(1,1,h*w,1),dim=2)).reshape(b,c,h,w)
return map_corre
# In[4]:
# Les fonctions de ce bloc sont utilisées pour appliquer le réseau à des fragments (pas à des patchs carrés)
# Cette fonction permet de sélectionner un ensemble de patchs carrés à partir d'un fragment
# Le paramètre “frag_size” fait ici référence à la taille du patch d'entrée carré (16 * 16)
# Le paramètre “seuillage” limite la proportion de pixels non noirs dans chaque patch
# Le paramètre “limite” peut limiter le nombre de correctifs trouvés dans chaque fragment
def get_patch_list(frag,frag_size,limite,seuillage):
n=0
m=0
h,w,c=frag.shape
patch_list=[]
position_list=[]
for i in range(4):
if len(patch_list)>limite and limite!=0:
break
for j in range(4):
if len(patch_list)>limite and limite!=0:
break
n_offset=i*4 # n offset
m_offset=j*4 # m offset
n=0
while n+frag_size+n_offset<h:
m=0
while m+frag_size+m_offset<w:
patch=frag[n+n_offset:n+frag_size+n_offset,m+m_offset:m+frag_size+m_offset,:]
if test_fragment32_32(patch,seuillage):
patch_list.append(patch)
position_list.append([int((n+frag_size/2)+n_offset),int((m+frag_size/2)+m_offset)])
m=m+frag_size
n=n+frag_size
return patch_list,position_list
# Entrez du fragment et de la fresque, exécutez le réseau
def run_net_v3(net,img,frag,frag_size,limite,seuillage,using_cuda,rotation):
Img=Image.fromarray(frag)
frag=np.array(Img.rotate(rotation))
img_tensor=img2tensor(img)
# la collection de patchs carrée dans le fragement "sont frag_list[]"
# La position de leur centre dans la fragment sont "position_frag[]"
frag_list,position_frag=get_patch_list(frag,frag_size,limite,seuillage)
if using_cuda:
img_tensor=img_tensor.cuda()
score_list=[]
coordonnee_list=[]
# Pour chaque patch carré dans la collection, effectuez un calcul en réseau de leur position
# Le résultat est placé en "coordonnee_list[]"
# "score_list[]" pas utile dans notre programme
for i in range(len(frag_list)):
frag_tensor=img2tensor(frag_list[i])
if using_cuda:
frag_tensor=frag_tensor.cuda()
res=net.forward(img_tensor,frag_tensor,using_cuda)
if using_cuda:
res=res.cpu()
score,po_h,po_w=show_coordonnee(res)
coordonnee_list.append([po_h,po_w])
score_list.append(score)
h_img,w_img,c=img.shape
position=[]
# Mettez les paires correspondante en "position[]"
# [x,y,x',y']
# La position (x,y) dans le fragment correspond à la position (x',y') dans la fresque
for i in range(len(coordonnee_list)):
x0=position_frag[i][0]
y0=position_frag[i][1]
x1=int(round(h_img*coordonnee_list[i][0]))
y1=int(round(w_img*coordonnee_list[i][1]))
position.append([x0,y0,x1,y1])
return score_list,position
# In[12]:
# Cette partie du code consiste à implémenter l'algorithme RANSAC amélioré
# Ecrire le point sous forme [x,y,1]T,
# Utilisé pour construire l'équation de la matrice de transformation
def creer_point(x,y):
p=np.zeros((3,1))
p[0][0]=x
p[1][0]=y
p[2][0]=1
return p
# Sélectionnez aléatoirement n points sans duplication à partir de M points
def selectionner_points(n,M):
table=[]
for i in range(M):
table.append(i)
result=[]
for i in range(n):
index=random.randint(0,M-i-1)
result.append(table[index])
table[index]=table[M-1-i]
return result
# Selon la matrice de transformation affine, calculer la position centrale transformée et l'angle de rotation
def position_rotation(h,centre_frag):
centre=h@centre_frag
cos_rot=(h[0][0]+h[1][1])/2
sin_rot=(h[1][0]-h[0][1])/2
tan_rot=sin_rot/(cos_rot+0.0000001)
if cos_rot>0:
rot_frag=math.atan(tan_rot)*(180/pi)
else:
rot_frag=math.atan(tan_rot)*(180/pi)+180
rot_frag=-rot_frag
if rot_frag>0:
rot_frag-=360
return centre[0][0],centre[1][0],rot_frag
# Vérifiez les résultats de Ransac en avec des changements de distance euclidienne
def test_frag(inline,frag,fres):
itera=10
frag_inline=[]
fres_inline=[]
# Metter les coordonnées du point inline dans "frag_inline[]",et "fres_inline[]"
for i in range(np.size(inline,0)):
if inline[i]==1:
frag_inline.append([frag[i][0],frag[i][1]])
fres_inline.append([fres[i][0],fres[i][1]])
p=[]
# Faites une boucle dix fois,
# sélectionnez à chaque fois deux paires correspondantes inline
# calculer le changement de leur distance euclidienne
for i in range(itera):
point_test=selectionner_points(2,np.size(frag_inline,0))
diff_x_frag=frag_inline[point_test[1]][0]-frag_inline[point_test[0]][0]
diff_y_frag=frag_inline[point_test[1]][1]-frag_inline[point_test[0]][1]
diff_frag=sqrt(pow(diff_x_frag,2)+pow(diff_y_frag,2))
diff_x_fres=fres_inline[point_test[1]][0]-fres_inline[point_test[0]][0]
diff_y_fres=fres_inline[point_test[1]][1]-fres_inline[point_test[0]][1]
diff_fres=sqrt(pow(diff_x_fres,2)+pow(diff_y_fres,2))
if diff_frag !=0:
fsf=diff_fres/diff_frag
p.append([fsf])
result=np.mean(p)
return result
def frag_match(frag,img,position):
frag_size=frag.shape
centre_frag=creer_point(frag_size[0]/2,frag_size[1]/2)
retained_matches = []
frag=[]
fres=[]
for i in range(len(position)):
frag.append([float(position[i][0]),float(position[i][1])])
fres.append([float(position[i][2]),float(position[i][3])])
if np.size(frag)>0:
# Calculer la matrice de transformation affine à l'aide de la méthode Ransac
h,inline=cv2.estimateAffinePartial2D(np.array(frag),np.array(fres))
# Si “h” n'est pas sous la forme de matrice 2 * 3, la matrice de transformation affine n'est pas trouvée
if np.size(h)!=6:
return ([-1])
else:
x,y,rot=position_rotation(h,centre_frag)
pourcenttage=sum(inline)/np.size(frag,0)
# Le nombre de points inline doit être supérieur à un certain nombre
if sum(inline)>3:
p=test_frag(inline,frag,fres)
# La distance euclidienne entre les points correspondants ne doit pas trop changer,
# sinon cela prouve que le résultat de Ransac est incorrect
# ici,le changement de la distance euclidienne sont entre 0.7 et 1.3
if abs(p-1)<0.3:
# Ce n'est qu'alors que Ransac renvoie le résultat correct
return([round(y),round(x),round(rot,3)])
else:
return ([-2])
else:
return ([-3])
else:
return ([-4])
# In[14]:
if __name__=="__main__":
frag_size=16
using_cuda=True
net=load_net("./net_trainned6000")
img_test=cv2.imread("./fresque0.ppm")
result=[]
for n in range(315):
if n<10:
frag_test=cv2.imread("./frag_eroded0/frag_eroded_000"+str(n)+".ppm")
elif n<100:
frag_test=cv2.imread("./frag_eroded0/frag_eroded_00"+str(n)+".ppm")
else:
frag_test=cv2.imread("./frag_eroded0/frag_eroded_0"+str(n)+".ppm")
# Faites pivoter les pièces de 20 degrés à chaque fois pour correspondre, répétez 18 fois
for i in range(18):
rotation=20*i
score_list,position=run_net_v3(net,img_test,frag_test,frag_size,60,0.7,using_cuda,rotation)
frag_position=frag_match(frag_test,img_test,position)
# Lorsque Ransac obtient le bon résultat, sortez de la boucle
if len(frag_position)==3:
rotation_base=i*20
break
# Enregistrez les fragments correctement localisés dans "result[]"
if len(frag_position)==3:
frag_position[2]=rotation_base-360-frag_position[2]
if frag_position[2]>0:
frag_position[2]=frag_position[2]-360
result.append([n,frag_position[0],frag_position[1],round(frag_position[2],3)])
# In[15]:
result

25
readme.txt Normal file
View file

@ -0,0 +1,25 @@
Notre code comprend deux parties.
1.L'apprentissage de réseaux neuronaux
"Apprentissage_MSELoss_avec_GPU.ipynb"
2.La fonctionnement de réseaux neuronaux
"Frag_Match_avec_rotation.ipynb"
***************************************************************************
Ce programme.ipynb peut être exécuté avec jupyter-notebook.
1.Ctrl+Alt+T Ouvrir le terminal
2.Input "jupyter-notebook" peut ouvrir une interface
3.Cliquez sur le programme pour l'ouvrir.
Il est recommandé d 'utiliser le programme jupyter-Notebook, qui non seulement fonctionne par blocs, mais aussi est configuré pour tous les environnements.
***************************************************************************
Si vous voulez utiliser le programme.py
"Apprentissage_MSELoss_avec_GPU.py"
et
"Frag_Match_avec_rotation.py"
1.Ctrl+Alt+T Ouvrir le terminal,Vous pouvez voir un "(base)" devant la ligne de commande.
2.Input instruction “conda activate py37” ,alors (base) va devenir (py37).
3.J'ai configuré l' environnement de py37 pour qu 'il fonctionne directement dans cet environnement.