121649982

无法用cmake生成2017工程文件

1

谁生成了，可以给我一个工程吗？或指导一下，感谢

标签文件示例

2

你好，可不可以给一下标签文件 的示例呢？非常感谢

how to train mobilenetv2 model

9

Thank you very much for your codebase. I have trained my own data with resnet50 successfully,but I when train it with mobilenet, the accuracy is very low. python main.py ucf101...

将min_sizes改为[[8, 16, 32], [64], [128]]，会报错，输出框个数是固定了的吗？

1

我是用来检测球，因为用原始的，需要放大2.5倍，才能用来检测乒乓球，才检测得到，这时帧率变得很低，所以我想调小这个 cfg = { 'name': 'FaceBoxes', #'min_dim': 1024, #'feature_maps': [[32, 32], [16, 16], [8, 8]], # 'aspect_ratios': [[1], [1], [1]], 'min_sizes': [[32, 64, 128], [256], [512]], # 'min_sizes': [[8, 16,...

could not broadcast input array from shape (506,641,3) into shape (506,640,3)

4

I encountered such a problem

训练乒乓球，振荡很大

1

你好，训练时loss变化很大，这个正常吗？ 2020-02-25 10:26:47,227[INFO]: cls_loss_score_1: --> 47.5173 2020-02-25 10:26:47,227[INFO]: reg_loss_bbox_1: --> 3581.6255 2020-02-25 10:26:47,227[INFO]: cls_loss_score_2: --> 555.4069 2020-02-25 10:26:47,227[INFO]: reg_loss_bbox_2: --> 1146.7589 2020-02-25 10:26:47,228[INFO]: cls_loss_score_3: --> 217.9907 2020-02-25 10:26:47,228[INFO]: reg_loss_bbox_3: -->...

train error

4

First of all,thank you for your great work. When I Train with one class.I encounter a problem.the loss always 0 2023-09-07 14:27:17,951 - pyskl - INFO - Config: model =...