-
Notifications
You must be signed in to change notification settings - Fork 898
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
How to set the batch size for prediction? #36
Comments
@o0windseed0o can you paste your complete config file here? It's probably an iteration boundary related bug somewhere in our code. |
@uduse Thanks for your reply! Please see the following.
There are several paramters in the config file that I don't know how to set, such as query_per_iter and bath_per_iter. Are there any instructions or introductions on how to write config files? As to the error, if it's not related to the config file, it might be the operation on generating batches, since the missing samples are always the last ones. |
Have you figured out what caused the problem? Or can anybody tell me which py file should be checked, related to the batch generator? |
@o0windseed0o haven't got a chance to dive into the problem yet. You might want to look at |
@uduse I have checked the PointerGenerator class, and I think the problem should be around the while True loop in the get_batch_generator function. There are no operations on how to deal with those samples that cannot be built up to a batch. Please check from here when you are free. Thank you! |
Need to figure out whether a bug exist. |
Today I come to the same situation: I have 5000 prediction samples, and it output 4998 predicts. @o0windseed0o Not sure if you have the duplicate sample. @bwanglzu By the way, can the model fixed the duplicate situation? |
Apparently there's something wrong in @Genie-Liu and you provide a bit more context? |
@faneshion any ideas? |
Hi all, I think it is possible to set the training batch size as 100 and predicting size as 10, right?
So I tried different sizes of predicting batch sizes, from 1, 10, to 100, after predicting, there are different results:
It is for binary classification using match_pyramid and predict totally 42,155 samples.
size = 1 numpy.core._internal.AxisError: axis 1 is out of bounds for array of dimension 1
size=10 predict and output predicting results for 42,142 samples
size=50 predict and output predicting results for 42,142 samples
size=100 predict and output predicting results for 42,092 samples
Anyone knows what was wrong?
The text was updated successfully, but these errors were encountered: