moondaiy

I just want to test your models.. Could you give me a models you have trained completed ? Thans a lot~

Thanks To your work . I have not download this project .But I would to know the time of this project,

关于训练集字符平衡问题

1

LZ大神好,请问下,是否统计过汉子字符出现的频率?是否平衡???

关于提供的model

6

你好,请问下,如下几个model是训练好的模型么 ImageNet mobilenet 07+12 RFB_Net300, BaiduYun Driver,FSSD300,SSD300 COCO RFB_Net512_E, BaiduYun Driver COCO RFB_Mobile Net300, BaiduYun Driver 我下载了 第一个 但是效果很差 用的是这个 RFB300_80_5.pth 文件

执行 demo/live.py出错

1

你好,我在执行demo/live.py 文件时, 发生了错误. Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #2 'weight' 我目前pytorch版本是0.3.0

Hi, In tensorflow, when using bach norm layer , we need to updata moving_mean and moving_vairous, so we need use this operation update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): train_op = optimizer.minimize(loss)...