Comments (10)
@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.
Related Issues (20)
- AttributeError: 'str' object has no attribute 'decode' HOT 3
- ImportError: cannot import name 'get_config' from 'tensorflow.python.eager.context'??
- How can I convert a keras model to yolov3 .weights file?
- How do you test model on data? HOT 1
- > 你好,我训练自己的数据集,win10+navida 3090+python3.6;执行train.py后,loss一直是nan,如何解决?请教指导,谢谢。
- width and height are resized to 416x416
- evaluate Model
- "Gradients do not exist" Warning
- "Epoch 00091:early stopping"It stops automatically when we get to step 90 HOT 1
- Does the model itself resize the image?
- low fps and no bounding box on Tensorflow 2 HOT 5
- AttributeError: 'str' object has no attribute 'decode' HOT 2
- how to use cudnn 7.1.4 ? HOT 2
- why the 2nd element of the yield in data_generator is of size equal to batch_size? HOT 1
- Training HOT 3
- Error when Data augmentation removed! Need help
- Questions about train model
- Adding metrics to the model HOT 1
- Error in loading annotaion labels while training HOT 1
- Encoding H264 not recognise after building open opencv manually
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from keras-yolo3.