Stargazer
Stargazer
> I think you have the same misunderstanding as in issue #112. After using `to_deterministic()`, the output of `augment_images()` is the same if the input is the same AND the...
@MhLiao This is weird, can you elaborate on your environment settings(os and cudnn version) and error messages?
@vinnitu @lijiaze2018 The Caffe version of this project is too old, and support for python3 is not good. I added all the special layers of CTPN based on the Caffe...
Same question.Did you find a way?
In this code, which object should I serialize? I've tried to use the method dump to serialize 'classifier',but it didn't work. PicklingError: Can't pickle
@MarkWuNLP Thanks for your answer. I still have some questions. There are two params,①params in function train_conv_net,②classifier.params. I assume that you mean the first one.When should I serialize the params?...
@Huarong Thanks for your answer. I assume that you mean the class is "class MLPDropout". And I save the class like this : ``` classifier.save('classifier.save') ``` It's the same error...
@MarkWuNLP I stored the params successfully too, but how do I use it to predict what I write? Could you show some examples? Like when and how I load the...
This seems to be just a warning, not sure if it will affect the results.
好的👍，目前我个人关注的优先级是：多模态模型>大语言模型>CV模型