如何解决输入尺寸为[?,64,64,512],[64]的'conv4_3_norm / mul'(op:'Mul')的尺寸必须相等,但为512和64的错误

时间:2019-10-27 13:00:20

标签: python ssd

我是python的新手,正在尝试使用SSD预先训练的模型来检测图像中的人物。错误: '尺寸必须相等,但对于'conv4_3_norm / mul'(op:'Mul'),输入形状为[?,64,64,512],[64]'error'

为512和64

继续出现,我不知道代码出了什么问题。该代码来自GitHub

model = ssd_512(image_size =(height,width,3),n_classes = 20,mode ='inference',l2_regularization = 0.0005,scales = [0.07,0.15,0.3,0.45,0.6,0.75,0.9,1.05] ,Aspect_ratios_per_layer = [[1.0,2.0,0.5],[1.0,2.0,0.5,3.0,1.0 / 3.0],[1.0,2.0,0.5,3.0,1.0 / 3.0],[1.0,2.0,0.5,3.0,1.0 /3.0],[1.0,2.0,0.5,3.0,1.0 / 3.0],[1.0,2.0,0.5],[1.0,2.0,0.5]],two_boxes_for_ar1 = True,steps = [8,16,32,64, 128、256、512],offsets = [0.5、0.5、0.5、0.5、0.5、0.5、0.5],clip_boxes = False,方差= [0.1、0.1、0.2、0.2],normalize_coords = True,subtract_mean = [123, 117,104],swap_channels = [2,1,0],confidence_thresh = 0.5,iou_threshold = 0.45,top_k = 200, nms_max_output_size = 400)

0 个答案:

没有答案