HandsLing

Results 27 issues of HandsLing

我想根据自己的使用场景,增加数据再训练一下流式语音识别,请问要训练example下面的哪个文件呢?

Question
Stale

from utils.cython_bbox import bbox_overlaps ImportError: No module named cython_bbox

when i was implement ASDN on faster rcnn,in the third stage,training faster_rcnn_adv,the loss of asdn was 0,could you tell me what should i change except the prototxt file?

hey,i was training the kittibox,but my result of evaluation were all zero, i was followed the steps in readme,what steps i missed? other results was right

请问一下,那些example下面的模型支持部署成流式模式呢?我尝试了librispeech和gigaspeech,转成流式的onnx都报错了

有人使用作者给的预训练权重微调之后能得到作者在代码里给出来的精度吗?我的精度不管是怎样都很低

i set the RPN_SCORE_THRESH = 0.90,and RPN_NMS_THRESH = 0.001 but the results have very much boxes that not include anything does anyone know how to solve it

请问作者你的运行环境是什么?运行时间显示的是多少呢? 我的运行环境是一块1080ti显卡,显示的运行时间是0.6-0.8秒左右一张 还有就是我看您使用的卷积操作全部是在一个convMD函数中,但是我将他们全部替换成tf.layer.conv2d和tf.layer.conv3d了,而且我将2D卷积替换成了标准的VGG16了,请问这样对网络会有影响吗?

我训练自己的模型,但是我只用了train文件夹进行训练,没有创建val文件夹也没有对应的文件,可是查看tensorboard有一个train_accuracy曲线,从1开始往下掉,到30多万次的时候降到了0.6几,请问这是怎么回事啊