-
Notifications
You must be signed in to change notification settings - Fork 491
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
ChannelPrunedLearner don't exec #175
Comments
This is log
I run pocket flow by some Learner, Can't run smoothly |
You mean the program does not have any outputs? Can you take a look at the GPU utility via |
nvidia-smi info:
I change |
Are you using the pre-defined models in PocketFlow, or are you using a self-defined model implemented by yourself? |
using a self-defined model implemented by myself |
Does |
Yes, but I want to know how to using a self-defined model implemented by myself. Can you tell me some method that positioning this problem. |
Can you post the code for your self-defined model ( |
I try change it, the code is too long. |
Or, can you upload the file? |
The file is also too many, I write a demo of my net. especially the dataset, I mock it and delete the data augmentation and pre-process.
my model helper:
my call func:
|
@jiaxiang-wu
I only define placeholder as |
I read the code in
Why edit the graph in
When train the pruned model in
|
I compress the model by ChannelPrunedLearner, when executed to
self.sess_train.run(self.train_op)
in__train_pruned_model(self, finetune=False)
fun, the program don't continue execution。 I don't know This is because my machine is too card or code error。my gpu card is Tesla K80。
the program stop at :
The text was updated successfully, but these errors were encountered: