Damon2019

hi ,can you change the default size of 300 to 512?thanks,looking forward to your reply

> 您好，我用的配置文件是fssd_vgg16_train_coco.yml,当我训练coco2017时conf_loss在5左右，loc_loss在2左右，一直不下去。我的配置文件如下： > MODEL: > SSDS: fssd > NETS: vgg16 > IMAGE_SIZE: [300, 300] > NUM_CLASSES: 81 > FEATURE_LAYER: [[[22, 34, 'S'], [512, 1024, 512]], > [['', 'S', 'S', 'S',...

@1453042287 @XiaSunny 你好，我想使用预训练模型 > TRAINABLE_SCOPE: 'base,norm,extras,loc,conf' RESUME_SCOPE: 'base,norm,extras,loc,conf' 这里面的参数我应该如何修改？ 谢谢！

> Excuse me，have you successfully changed the data set and trained? > If you succeed, can you tell me how to do that? hi,i also meet this problem.Can you tell...

@zzf005 @guangqianqin hi,How did you train your own dataset?could you give me some suggest?plz!

> @zzf005 @guangqianqin hi,How did you train your own dataset?could you give me some suggest?plz! I succeed

I tried the training on COCO dataset ,can anyone tell me how to modify the coco_labels.txt?

@ztianlin hi,can you tell me how to evaluate COCO dataset,thanks

May I ask how to use GPU to calculate the time of pictures