weixiaolian21

剪枝后的模型使用darknet训练的话效果正常，但是使用caffe这个代码训练的话的话大概相差7个百分点的map，请问这其中会有什么问题吗？

IOError: Unable to create file

1

hello，when i run this code，the following error encountered. I don`t konw why. 2048/2055 [============================>.] - ETA: 0s - loss: 4.8819 - acc: 0.2090Epoch 00000: val_loss improved from inf to 4.92003,...

the loss will be nan sometime due to tf.log(). ` L = -labels*(1-alpha)*((1-y_pred)**gamma)*tf.log(tf.clip_by_value(y_pred, 1e-8, 1.0)) -\ (1-labels)*alpha*(y_pred**gamma)*tf.log(tf.clip_by_value(1.0 - y_pred, 1e-8, 1.0)) `

rk3588 连板调试报错，adb能连上

3

--> Init runtime environment I target set by user is: rk3588 I Starting ntp or adb, target is RK3588 I Start adb... I Connect to Device success! I NPUTransfer: Starting...

怎么连接 linux中的rknn_server

2

rk3588+linux 想要使用rknntoolkit进行调试 无法用adb连接linux系统的板子

about the yolov3-tiny-prn.cfg

7

hi, thanks for your work. can you tell me where is the PRN module in this cfg? I just find some shotcut layer and the shortcut layer seems to add...

how to get libncnn.a

1

i want compile this code in arm，there is something wrong about this library