520 lines
36 KiB
Text
Executable file
520 lines
36 KiB
Text
Executable file
{
|
||
"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",
|
||
"\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",
|
||
"# Obtenez des données d'entraînement\n",
|
||
"# frag,vt=get_training_fragment(frag_size,image)\n",
|
||
"# frag est un patch carrée de taille (frag_size*frag_size) a partir du image(Son emplacement est aléatoire)\n",
|
||
"# vt est la vérité terrain de la forme Dirac.\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",
|
||
" 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",
|
||
"# Charger un fragment d'entrainement\n",
|
||
"# Les fragments sont chargés comme des images et les véritées terrain sont générées\n",
|
||
"def load_training_fragment(frag_path,vt_path,using_cuda):\n",
|
||
" frag=cv2.imread(im_path)\n",
|
||
" with open(vt_path, 'r') as f:\n",
|
||
" data_vt = f.readlines()\n",
|
||
" \n",
|
||
" if using_cuda:\n",
|
||
" frag=frag.cuda()\n",
|
||
" vt=vt.cuda()\n",
|
||
" \n",
|
||
"\n",
|
||
"# Cette fonction convertit l'image en variable de type Tensor.\n",
|
||
"# Toutes les données de calcul du réseau sont de type Tensor\n",
|
||
"# Img.shape=[Height,Width,Channel]\n",
|
||
"# Tensor.shape=[Batch,Channel,Height,Width]\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",
|
||
"# Trouvez les coordonnées de la valeur maximale dans une carte de corrélation\n",
|
||
"# x,y=show_coordonnee(carte de corrélation)\n",
|
||
"def show_coordonnee(position_pred):\n",
|
||
" map_corre=position_pred.squeeze().detach().numpy()\n",
|
||
" h,w=map_corre.shape\n",
|
||
" max_value=map_corre.max()\n",
|
||
" coordonnee=np.where(map_corre==max_value)\n",
|
||
" return coordonnee[0].mean()/h,coordonnee[1].mean()/w\n",
|
||
"\n",
|
||
"# Filtrer les patchs en fonction du nombre de pixels noirs dans le patch\n",
|
||
"# Si seuls les pixels non noirs sont plus grands qu'une certaine proportion(seuillage), revenez à True, sinon False\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",
|
||
"# Ces deux fonctions permettent de sauvegarder le réseau dans un fichier\n",
|
||
"# ou de load le réseau stocké à partir d'un fichier\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",
|
||
"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": 6,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Créer un poids de type DeepMatch comme valeur initiale de Conv1 (non obligatoire)\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",
|
||
"# Calculer le poids initial de la couche convolutive add\n",
|
||
"# n, m signifie qu'il y a n * m sous-patches dans le patch d'entrée\n",
|
||
"# Par exemple, le patch d'entrée est 16 * 16, pour les patchs 4 * 4 de la première couche, n = 4, m = 4\n",
|
||
"# pour les patchs 8 * 8 de la deuxième couche, n = 2, m = 2\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",
|
||
"# Calculer le poids initial de la couche convolutive shift\n",
|
||
"# shift+add Peut réaliser l'étape de l'agrégation\n",
|
||
"# Voir ci-dessus pour les paramètres n et m. \n",
|
||
"# Pour des étapes plus détaillées, veuillez consulter mon rapport de stage\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",
|
||
"# Trouvez le petit patch(4 * 4) dans la n ème ligne et la m ème colonne du patch d'entrée\n",
|
||
"# Ceci est utilisé pour calculer la convolution et obtenir la carte de corrélation\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 dans le patch d'entrée\n",
|
||
" m=int(w_fr/psize)\n",
|
||
" \n",
|
||
" self.conv1 = nn.Conv2d(3,8,kernel_size=3,stride=1,padding=1)\n",
|
||
" # Si vous souhaitez initialiser Conv1 avec les poids de DeepMatch, exécutez la ligne suivante\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:# Si n=m=1，Notre réseau n'a plus besoin de plus de couches pour agréger les cartes de corrélation\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",
|
||
" def get_descripteur(self,img,using_cuda):\n",
|
||
" # Utilisez Conv1 pour calculer le descripteur,\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",
|
||
" # Ajouter une couche constante pour éviter la division par 0 lors de la normalisation\n",
|
||
" descripteur_img=torch.cat((descripteur_img,couche_constante),1)\n",
|
||
" # la normalisation\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",
|
||
" # Utilisez Conv1 pour calculer le descripteur,\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",
|
||
" #######################################\n",
|
||
" # Calculer la carte de corrélation par convolution pour les n*m patchs plus petit.\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",
|
||
" ########################################\n",
|
||
" # Étape de polymérisation\n",
|
||
" map_corre=self.maxpooling(map_corre)\n",
|
||
" map_corre=self.shift1(map_corre)\n",
|
||
" map_corre=self.add1(map_corre)\n",
|
||
" \n",
|
||
" #########################################\n",
|
||
" # Répétez l'étape d'agrégation jusqu'à obtenir le graphique de corrélation du patch d'entrée\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",
|
||
" # Normalisation de la division par maximum\n",
|
||
" map_corre=map_corre/(map_corre.max())\n",
|
||
" # Normalisation SoftMax\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": [
|
||
"def run_net(net,img,frag,frag_size,using_cuda):\n",
|
||
" h,w,c=frag.shape\n",
|
||
" n=int(h/frag_size)\n",
|
||
" m=int(w/frag_size)\n",
|
||
" frag_list=[]\n",
|
||
" #####################################\n",
|
||
" # Obtenez des patchs carrés des fragments et mettez-les dans la frag_list\n",
|
||
" for i in range(n):\n",
|
||
" for j in range(m):\n",
|
||
" frag_32=frag[i*frag_size:(i+1)*frag_size,j*frag_size:(j+1)*frag_size]\n",
|
||
" if test_fragment32_32(frag_32,0.6):\n",
|
||
" frag_list.append(frag_32)\n",
|
||
" img_tensor=img2tensor(img)\n",
|
||
" ######################################\n",
|
||
" if using_cuda:\n",
|
||
" img_tensor=img_tensor.cuda()\n",
|
||
" \n",
|
||
" coordonnee_list=[]\n",
|
||
" #######################################\n",
|
||
" # Utilisez le réseau pour calculer les positions de tous les patchs dans frag_list[]\n",
|
||
" # Mettez le résultat du calcul dans coordonnee_list[]\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",
|
||
" po_h,po_w=show_coordonnee(res)\n",
|
||
" coordonnee_list.append([po_h,po_w])\n",
|
||
" h_img,w_img,c=img.shape\n",
|
||
" position=[]\n",
|
||
" for i in range(len(coordonnee_list)):\n",
|
||
" x=int(round(h_img*coordonnee_list[i][0]))\n",
|
||
" y=int(round(w_img*coordonnee_list[i][1]))\n",
|
||
" position.append([x,y])\n",
|
||
" return position"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"if __name__=='__main__':\n",
|
||
" \n",
|
||
" # La taille du patch d'entrée est de 16*16\n",
|
||
" frag_size=16\n",
|
||
" # La taille du plus petit patch dans réseau est de 4 *4 fixée\n",
|
||
" psize=4\n",
|
||
" using_cuda=True\n",
|
||
" \n",
|
||
" \n",
|
||
" net=Net(frag_size,psize)\n",
|
||
" \n",
|
||
" # Pour chaque fresque, le nombre d'itérations est de 1000\n",
|
||
" itera=1000\n",
|
||
" \n",
|
||
" if using_cuda:\n",
|
||
" net=net.cuda()\n",
|
||
" \n",
|
||
" # Choisissez l'optimiseur et la fonction de coût\n",
|
||
" optimizer = torch.optim.Adam(net.parameters())\n",
|
||
" loss_func = torch.nn.MSELoss()\n",
|
||
" \n",
|
||
" # Dans le processus d'apprentissage du réseau,le changement d'erreur est placé dans loss_value=[] \n",
|
||
" # et le changement de Conv1 poids est placé dans para_value[]\n",
|
||
" loss_value=[]\n",
|
||
" para_value=[]\n",
|
||
" ####################################################training_net\n",
|
||
" \n",
|
||
" #Les données d'entraînement sont 6 fresques\n",
|
||
" N_fresque = 6\n",
|
||
" for fresque_id in range(N_fresque):\n",
|
||
" im_path=\"./training_data/fresque{}.ppm\".format(fresque_id)\n",
|
||
" img_training=cv2.imread(im_path)\n",
|
||
" h,w,c=img_training.shape\n",
|
||
" \n",
|
||
" # Si la peinture murale est trop grande, sous-échantillonnez-la et rétrécissez-la\n",
|
||
" while h*w>(1240*900):\n",
|
||
" img_training=cv2.resize(img_training,(int(h/2),int(w/2)),interpolation=cv2.INTER_CUBIC)\n",
|
||
" h,w,c=img_training.shape\n",
|
||
" im_tensor=img2tensor(img_training)\n",
|
||
" \n",
|
||
" if using_cuda:\n",
|
||
" im_tensor=im_tensor.cuda()\n",
|
||
" for i in range(itera):\n",
|
||
" # Tous les 100 cycles, enregistrez le changement de poids\n",
|
||
" if i%100==0:\n",
|
||
" para=net.conv1.weight\n",
|
||
" para=para.detach().cpu()\n",
|
||
" para_value.append(para)\n",
|
||
" frag,vt=get_training_fragment(frag_size,img_training)\n",
|
||
" frag_tensor=img2tensor(frag)\n",
|
||
" if using_cuda:\n",
|
||
" vt=vt.cuda()\n",
|
||
" frag_tensor=frag_tensor.cuda()\n",
|
||
" # Utilisez des patchs et des fresques de données d'entraînement pour faire fonctionner le réseau\n",
|
||
" frag_pred=net.forward(im_tensor,frag_tensor,using_cuda)\n",
|
||
" b,c,h,w=vt.shape\n",
|
||
" # Utilisez la fonction de coût pour calculer l'erreur\n",
|
||
" err_=loss_func(vt,frag_pred)\n",
|
||
" # Utilisez l'optimiseur pour ajuster le poids de Conv1\n",
|
||
" optimizer.zero_grad()\n",
|
||
" err_.backward(retain_graph=True)\n",
|
||
" optimizer.step()\n",
|
||
" \n",
|
||
" loss_value.append(err_.tolist())\n",
|
||
" \n",
|
||
" del frag_tensor,frag_pred,err_,vt\n",
|
||
" torch.cuda.empty_cache()\n",
|
||
" \n",
|
||
" # sauvegarder le réseau dans le fichier \"net_trainned6000\"\n",
|
||
" file_path=\"./net_trainned6000\"\n",
|
||
" save_net(file_path,net)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"6000"
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"len(loss_value)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"[<matplotlib.lines.Line2D at 0x7f2b3292d048>]"
|
||
]
|
||
},
|
||
"execution_count": 11,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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\n",
|
||
"text/plain": [
|
||
"<Figure size 432x288 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.plot(loss_value)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"file_path=\"./net_trainned6000\"\n",
|
||
"save_net(file_path,net)"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.8.5"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 4
|
||
}
|