Sign up to take part
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
build_train_sequence_with_batch_size
Added on May 29, 2023 11:27AM
Likes: 0
Replies: 2
wanggaige21
Dataiku DSS Core Designer, Dataiku DSS ML Practitioner, Registered Posts: 2 ✭✭✭
Dear experts,
Where can I find detailed api parameters information of deep learning related functions?
Such as "build_train_sequence_with_batch_size", I want to manually edit the training targets.
Best Regards
Wang Gaige
Answers
-
Alexandru Dataiker, Dataiku DSS Core Designer, Dataiku DSS ML Practitioner, Dataiku DSS Adv Designer, Registered Posts: 1,254 DataikerHi,
You can find an example of build_train_sequence_with_batch_size usage here :https://doc.dataiku.com/dss/latest/machine-learning/deep-learning/advanced.html#build-sequence
Thanks, -
Hi, AlexT,
Thanks for your answer. But what I want to do is changing the training input, such as the one hot encoding results. I need to know how to get the output of this function, which is similar to keras codes.
class MyDataFrameIterator(image.DataFrameIterator):
def __getitem__(self, idx):
X_, y_ = super().__getitem__(idx)
y_ = np.delete(y_, self.class_indices['Negative'], axis=1)
return X_, y_
def next(self):
X_, y_ = super().next()
y_ = np.delete(y_, self.class_indices['Negative'], axis=1)
return X_, y_