huangzicheng issues

Results 12 issues of


                                            huangzicheng

KeyError: "The name 'embeddings:0' refers to a Tensor which does not exist. The operation, 'embeddings', does not exist in the graph."

when i run validate_on_lfw.py, it always show that error.........i have used trian_softmax.py training results to run validate_on_lfw.py ， it was also....could give some help.....@davidsandberg

你好，gc_prune.py里面对分组卷积后的model参数保存，可否提供下代码

i change detector ,use FCOS instead of YOlO, The effect of pedestrian detection is good, i want to Detect a frame to track 10 frames,it seem some trouble,can you show your code for real time processing

COCO 测试减枝map 很低?

用coco数据集得到减枝的map很低 ![2019-08-26 09-11-03屏幕截图](https://user-images.githubusercontent.com/30286349/63659164-699ddb00-c7e2-11e9-9997-bb882f08240c.png)

您好，那个add_colour的程序主程序是哪个，怎么添加图片进去，这个和labelme标注的xml文件有关吗？我没有找到路径。

ｏｎｎｘ　ｄｏｅｓｎ＇ｔ　support GroupNorm

RuntimeError: [enforce fail at elementwise_ops_utils.cc:56] A_dim == B_dim || A_dim == 1 || B_dim == 1. Error from operator: input: "1082" input: "1084" output: "1085" name: "" type: "Add" device_option...

type(self).name, name)) AttributeError: 'YOLOv3' object has no attribute 'module'

Test results are bad，when I train 120 epoch, it class confidence are so low，is lower than 0.0001

where is 'syn_bg.jpg'? it seem not right

syn_bg = cv2.imread(os.path.join(savedir,'syn_bg.jpg'))

train for voc dataset

you could use the [code](https://github.com/huangzicheng/CornerNet-Lite) here ! please give me a star