xfby
xfby
Hello, have you ever tested the time-consuming reasoning for each image?I face almost real-time detection scene , and I don't know if the algorithm is suitable，thanks very much
Is the size of the input image unadjustable(resize, cropsize)? I get error after changing resize and cropsize. The inference stage, how to deal with larger images, such as 900*1000, resize...
您好，感谢您的开源实现，我在自己的数据集上进行测试效果很好，但是有个问题，我的数据集图片可能是包含多种不同纹理背景的正样本，我发现训练单一纹理背景的数据集效果不错，但仅对该纹理背景有效，尝试将不同背景的图片一起训练却很难收敛，想请问下有没有什么方法可以训练一个通用模型，或者说可以做哪方面的优化可以将 MVTec AD 数据集里leather、wood等样本一起训练？感谢！
目标变量201个、决策变量1077个；代码如下： 问题定义： > class ppproblem(ea.Problem): # 继承Problem父类 def __init__(self,marklist,marklist_iddata_dict): name = 'Trinasolar—power-predict-stage2-v2' # 初始化name（函数名称，可以随意设置） M = 3*len(marklist_iddata_dict) #优化目标个数 maxormins = [1,1,1]*len(marklist_iddata_dict) # （目标最小最大化标记列表，1：最小化该目标；-1：最大化该目标) Dim = 16*len(marklist_iddata_dict) # 初始化Dim（决策变量维数）def dim(a,b,c) varTypes...
Hello, have you ever tested the mvtec dataset accuracy? I tested the auroc of the carpet category with only 0.49，It is very different from the paper. Is there any guidance...
关于字体字符效果
您好，如何生成残缺字符，或者手写字符？
您好，如题，如果想生成图片及对应的字符位置坐标与label的数据是否可以？类似于coco数据集
Thank you for your work! Can you provide training data for the xgboost model?
Excellent job, I want to use it for object detection in specific datasets, but how to prepare my own dataset or what steps should I follow? Thank you again！