Update app.py

app.py

@@ -3,47 +3,38 @@ import os
 os.system('pip3 install torch torchvision')# torchaudio')
 
 #pip3 install torch  -q')
-import torch
 import sys
 import numpy as np
-from PIL import Image
-import itertools
-import glob
 import random
+import matplotlib.pyplot as plt
+import tqdm
 import torch
-import torchvision
-import torchvision.transforms as transforms
-import torch.nn as nn
-import torch.optim as optim
-import torch.nn.functional as F
 from codes import *
 
-## Print samples
 
-from torchvision.models import resnet18
+#device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+x_t,y_t = generate_standard_elips(N_samples = 30, a= 0.8,b = 1.5)
+pointcloud_target = To_pointcloud(x_t,y_t)
 
+dim = 1.5
+RefRotation, Translation = random_rigid_transformation(dim=dim)
+pointcloud_source = np.matmul(RefRotation, pointcloud_target.T).T + Translation
+x_s, y_s, z_s = To_xyz(pointcloud_source)
 
-#device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
-with_points = True
-dim = 128
-dim0 =224
-crop_ratio = dim/dim0
+PC1_mean = np.mean(pointcloud_source, axis=0)
+pointcloud_source_norm = pointcloud_source - PC1_mean
+
+PC2_mean = np.mean(pointcloud_target, axis=0)
+pointcloud_target_norm = pointcloud_target - PC2_mean
+
+x_sn, y_sn, z_sn = To_xyz(pointcloud_source_norm)
+x_tn, y_tn, z_tn = To_xyz(pointcloud_target_norm)
+
+pointcloud_source_norm_torch = torch.tensor(pointcloud_source_norm, requires_grad=False).to(torch.float32)
+pointcloud_target_norm_torch = torch.tensor(pointcloud_target_norm, requires_grad=False).to(torch.float32)
 
-file_savingfolder = './modelbest/'
-ext = '_bestVal'
-core_model_tst = resnet18(pretrained=True)
-core_model_tst.fc = Identity()
-core_model_tst.load_state_dict(torch.load(file_savingfolder+'core_model'+ext+'.pth', map_location=torch.device('cpu') ))
-#core_model_tst.to(device)
-IR_Model_tst = Build_IRmodel_Resnet(core_model_tst, registration_method)
-IR_Model_tst.load_state_dict(torch.load(file_savingfolder+'IR_Model'+ext+'.pth', map_location=torch.device('cpu')))
-#IR_Model_tst.to(device)
-IR_Model_tst.eval()
 
-def imgnt_reg(img1,img2):#, model_selected):
-    #fixed_images = np.empty((1, 128, 128, 3))
-    #moving_images = np.empty((1, 128, 128, 3))
-    # prepare inputs:
+def imgnt_reg(img1,img2):
     fixed_images = preprocess_image(img1, dim = 128)
     moving_images = preprocess_image(img2, dim = 128)
     M_i = torch.normal(torch.zeros([1,2,3]), torch.ones([1,2,3]))