import numpy as np import pandas as pd import matplotlib.pyplot as plt import PIL import torch from torchvision import transforms import torchvision #调用已经训练好的FCN语义分割网络 model = torchvision.models.segmentation.fcn_resnet101(pretrained=True) model.eval() #读取照片 image=PIL.Image.open('1234.jpg') #照片进行预处理 image_transf=transforms.Compose([ transforms.ToTensor(), transforms.Normalize(mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225]) ] ) image_tensor=image_transf(image).unsqueeze(0) output=model(image_tensor)['out'] output.shape #读取图片,进行分割,总共21个通道,因为在21个数据集上训练 #转化为2维图像 outputarg=torch.argmax(output.squeeze(),dim=0).numpy() outputarg def decode_seqmaps(image,label_colors,nc=21): r=np.zeros_like(image).astype(np.uint8) g=np.zeros_like(image).astype(np.uint8) b=np.zeros_like(image).astype(np.uint8) for cla in range(0,nc): idx = image == cla r[idx] = label_colors[cla,0] g[idx] = label_colors[cla,1] b[idx] = label_colors[cla,2] rgbimage= np.stack([r,g,b],axis=2) return rgbimage import os os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE" label_colors =np.array([(0,0,0), #0=background (128,0,0),(0,128,0),(128,128,0),(0,0,128), #1=airplane,2=bicycle,3=bird,4=boat (128,0,128),(0,128,128),(128,128,128),(64,0,0), #6=bus,7=car,8=cat,9=chair (192,0,0),(64,128,0),(192,128,0),(64,0,128), #10=cow,11=dining table,12=dog,13=horse (192,0,128),(64,128,128),(192,128,128),(0,64,0), #14=motorbike,15=person,16=potted plant,17=sheep (128,64,0),(0,192,0),(128,192,0),(0,64,128) #18=sofa,19=train,20=tv/monitor ]) outputrgb=decode_seqmaps(outputarg,label_colors) plt.figure(figsize=(20,8)) plt.subplot(1,2,1) plt.imshow(image) plt.axis('off') plt.subplot(1,2,2) plt.imshow(outputrgb) plt.axis('off') plt.subplots_adjust(wspace=0.05) plt.show()使用了哪些深度学习的模型和方法