-
Notifications
You must be signed in to change notification settings - Fork 31
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Keras-Tensorflow version problem #3
Comments
hello ,dear |
tf=1.14,keras=2.2.4 |
Yeah, the problem has been solved by the env: |
thanks ,
|
what is your python version? |
Python 3.6.8rc1 (v3.6.8rc1:cc3e73212a, Dec 12 2018, 00:15:46) [MSC v.1900 64 bit (AMD64)] on win32 |
My roommate just tested the environment on Python 3.5.5 with He worked on Ubuntu 16.04 with Intel CPUs and 1080 GPU. |
py 3.5.2 tf-gpu=1.12 keras=2.24 也是不行 |
这个有点奇怪,我和室友都正常可以用的 |
大佬,为啥我重新用imageai训练,采用作者的脚本,训练200次,最多才62%啊? |
Could you please use the general language here? Maybe I have the same issue and now can't correctly read your comments... |
Chinese is the common language,哈哈,大家都在说中文,中文好听。 |
as you can see in all of the issues here english is the most common and most used language. Please use english here in the issue section as other like me cannot read the comments in chinese... Edit: Google Translator: "哈哈,大家都在说中文,中文好听。" => "Haha, everyone is speaking Chinese, and it sounds good." |
I met some problems while executing 'load_model' function.
My env:
python==3.6
tensorflow==1.4.0
keras==2.0.8
Error:
ValueError Traceback (most recent call last)
in
----> 1 model = load_model("action_net_ex-060_acc-0.745313.h5")
ValueError: Unknown initializer: GlorotUniform
Could you please specify your testing versions of tf and keras?
Thanks!
The text was updated successfully, but these errors were encountered: