十年网站开发经验 + 多家企业客户 + 靠谱的建站团队
量身定制 + 运营维护+专业推广+无忧售后,网站问题一站解决
这篇文章将为大家详细讲解有关使用pytorch怎么实现一个可视化中间层,文章内容质量较高,因此小编分享给大家做个参考,希望大家阅读完这篇文章后对相关知识有一定的了解。
让客户满意是我们工作的目标,不断超越客户的期望值来自于我们对这个行业的热爱。我们立志把好的技术通过有效、简单的方式提供给客户,将通过不懈努力成为客户在信息化领域值得信任、有价值的长期合作伙伴,公司提供的服务项目有:国际域名空间、虚拟空间、营销软件、网站建设、镇赉网站维护、网站推广。import cv2 import numpy as np import torch from torch.autograd import Variable from torchvision import models #创建30个文件夹 def mkdir(path): # 判断是否存在指定文件夹,不存在则创建 # 引入模块 import os # 去除首位空格 path = path.strip() # 去除尾部 \ 符号 path = path.rstrip("\\") # 判断路径是否存在 # 存在 True # 不存在 False isExists = os.path.exists(path) # 判断结果 if not isExists: # 如果不存在则创建目录 # 创建目录操作函数 os.makedirs(path) return True else: return False def preprocess_image(cv2im, resize_im=True): """ Processes image for CNNs Args: PIL_img (PIL_img): Image to process resize_im (bool): Resize to 224 or not returns: im_as_var (Pytorch variable): Variable that contains processed float tensor """ # mean and std list for channels (Imagenet) mean = [0.485, 0.456, 0.406] std = [0.229, 0.224, 0.225] # Resize image if resize_im: cv2im = cv2.resize(cv2im, (224, 224)) im_as_arr = np.float32(cv2im) im_as_arr = np.ascontiguousarray(im_as_arr[..., ::-1]) im_as_arr = im_as_arr.transpose(2, 0, 1) # Convert array to D,W,H # Normalize the channels for channel, _ in enumerate(im_as_arr): im_as_arr[channel] /= 255 im_as_arr[channel] -= mean[channel] im_as_arr[channel] /= std[channel] # Convert to float tensor im_as_ten = torch.from_numpy(im_as_arr).float() # Add one more channel to the beginning. Tensor shape = 1,3,224,224 im_as_ten.unsqueeze_(0) # Convert to Pytorch variable im_as_var = Variable(im_as_ten, requires_grad=True) return im_as_var class FeatureVisualization(): def __init__(self,img_path,selected_layer): self.img_path=img_path self.selected_layer=selected_layer self.pretrained_model = models.vgg16(pretrained=True).features #print( self.pretrained_model) def process_image(self): img=cv2.imread(self.img_path) img=preprocess_image(img) return img def get_feature(self): # input = Variable(torch.randn(1, 3, 224, 224)) input=self.process_image() print("input shape",input.shape) x=input for index,layer in enumerate(self.pretrained_model): #print(index) #print(layer) x=layer(x) if (index == self.selected_layer): return x def get_single_feature(self): features=self.get_feature() print("features.shape",features.shape) feature=features[:,0,:,:] print(feature.shape) feature=feature.view(feature.shape[1],feature.shape[2]) print(feature.shape) return features def save_feature_to_img(self): #to numpy features=self.get_single_feature() for i in range(features.shape[1]): feature = features[:, i, :, :] feature = feature.view(feature.shape[1], feature.shape[2]) feature = feature.data.numpy() # use sigmod to [0,1] feature = 1.0 / (1 + np.exp(-1 * feature)) # to [0,255] feature = np.round(feature * 255) print(feature[0]) mkdir('./feature/' + str(self.selected_layer)) cv2.imwrite('./feature/'+ str( self.selected_layer)+'/' +str(i)+'.jpg', feature) if __name__=='__main__': # get class for k in range(30): myClass=FeatureVisualization('/home/lqy/examples/TRP.PNG',k) print (myClass.pretrained_model) myClass.save_feature_to_img()
关于使用pytorch怎么实现一个可视化中间层就分享到这里了,希望以上内容可以对大家有一定的帮助,可以学到更多知识。如果觉得文章不错,可以把它分享出去让更多的人看到。
另外有需要云服务器可以了解下创新互联scvps.cn,海内外云服务器15元起步,三天无理由+7*72小时售后在线,公司持有idc许可证,提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案,具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势,专为企业上云打造定制,能够满足用户丰富、多元化的应用场景需求。