How to train yolo.h5 just using one class "person"? What changes should I do? about keras-yolo3 HOT 10 CLOSED

@qqwweee Hello,
Now the code can run sucessfully. I just reboot my computer. Then I change the the class to be ["person", "background"]. But my aim is still to detection people. And I set smaller learning rate . Like this below:
` learning_rate = 0.000001

my_adam = optimizers.Adam(lr=learning_rate, beta_1=0.9, beta_2=0.999,
                          epsilon=1e-08)
model.compile(optimizer=my_adam, loss={
    # use custom yolo_loss Lambda layer.
    'yolo_loss': lambda y_true, y_pred: y_pred})`

But the loss is still nan.

`Epoch 1/30

3/4784 [..............................] - ETA: 10:03:21 - loss: nan
6/4784 [..............................] - ETA: 5:05:07 - loss: nan
9/4784 [..............................] - ETA: 3:25:19 - loss: nan
12/4784 [..............................] - ETA: 2:40:57 - loss: nan
15/4784 [..............................] - ETA: 2:09:35 - loss: nan
18/4784 [..............................] - ETA: 1:49:04 - loss: nan
21/4784 [..............................] - ETA: 1:33:59 - loss: nan
24/4784 [..............................] - ETA: 1:23:32 - loss: nan
27/4784 [..............................] - ETA: 1:14:58 - loss: nan
30/4784 [..............................] - ETA: 1:08:00 - loss: nan
33/4784 [..............................] - ETA: 1:02:37 - loss: nan`

from keras-yolo3.

same issue. Do you also get warnings about not loading layer weights due to shape mismatch? @sunshinezhihuo

from keras-yolo3.

same issue +1 just want one category localization, got loss nan and some warning as @ifeherva said

from keras-yolo3.

@Zhangheng-Fighter same issue +1 我也是训练到后面nan了,换学习率啥的还是nan.....

from keras-yolo3.

@ifeherva @qqwweee same issue +1, also changed the learning rate to 0.0001, loss still be nan.

from keras-yolo3.

what is the solution to this? Same issue here

from keras-yolo3.

@ybbtuubj 你在训练的时候有修改cfg文件重新生产新的h5预训练模型了吗？

from keras-yolo3.

我修改了cfg，也是遇到了相同问题，训练损失有，但是每轮训练完验证损失都是nan！你解决了吗？，朋友@Pichairen

from keras-yolo3.

我修改了cfg，也是遇到了相同问题，训练损失有，但是每轮训练完验证损失都是nan！你解决了吗？，朋友@Pichairen

Me too

from keras-yolo3.

I have the same problem. Any solution now?

from keras-yolo3.