yoloX obj_struct[“difficult“] = int(obj.find(“difficult“).text)问题解决

yoloX obj_struct[“difficult”] = int(obj.find(“difficult”).text)问题解决

yoloX模型默认运行到10个epoch有一个测试，然后我是在测试的时候报错，报错位置在voc_eval.py文件下，相对位置为：

yolox/evaluators/voc_eval.py

报这个错主要原因是标签文件.xml中没有difficult这个类，我们可以直接简单粗暴地注释掉报错行24，即

 # obj_struct["difficult"] = int(obj.find("difficult").text)

但是如果直接这样还是会报错，因为下面还是用到了difficult类。大约在100-110行的位置

    # extract gt objects for this class
    class_recs = {}
    npos = 0
    for imagename in imagenames:
        R = [obj for obj in recs[imagename] if obj["name"] == classname]
        bbox = np.array([x["bbox"] for x in R])
        difficult = np.array([x["difficult"] for x in R]).astype(np.bool)
        det = [False] * len(R)
        npos = npos + sum(~difficult)
        class_recs[imagename] = {"bbox": bbox, "difficult": difficult, "det": det}

因为difficult类是用来判断该object是不是困难样本的，我们如果xml里面没有这个类，那我们可以认为所有object都是不困难的。因此可以这样改：

    # extract gt objects for this class
    class_recs = {}
    npos = 0
    for imagename in imagenames:
        R = [obj for obj in recs[imagename] if obj["name"] == classname]
        bbox = np.array([x["bbox"] for x in R])
        # difficult = np.array([x["difficult"] for x in R]).astype(np.bool)
        difficult = np.array([0 for x in R]).astype(np.bool)
        det = [False] * len(R)
        npos = npos + sum(~difficult)
        class_recs[imagename] = {"bbox": bbox, "difficult": difficult, "det": det}

这样就OK了。