i'm a newbie in programming. I try to use this library. it's very useful for me.
I want to show centroid in K-means clustering. how to show it? thank u so much..

Hi I would like to propose a better implementation for 'test_indices':

We can remove the unneeded np.array casting:

Cleaner/New:
test_indices = list(set(range(len(texts))) - set(train_indices))

Old:
test_indices = np.array(list(set(range(len(texts))) - set(train_indices)))

I tried some RNN regression learning based on the code in the "PyTorch-Tutorial/tutorial-contents/403_RNN_regressor.py" file, which did not work for me at all.

According to an accepted answer on stack-overflow (https://stackoverflow.com/questions/52857213/recurrent-network-rnn-wont-learn-a-very-simple-function-plots-shown-in-the-q?noredirect=1#comment92916825_52857213), it turns out that the li

best triplet loss ever

https://github.com/adambielski/siamese-triplet
https://github.com/andreasveit/triplet-network-pytorch
https://github.com/CoinCheung/triplet-reid-pytorch
https://discuss.pytorch.org/t/triplet-loss-in-pytorch/30634

The procedure for downloading the "en_vectors_web_lg" in spacy. by downloading and unzipping the file, and shifting it to the appropriate directory, as illustrated here is l

Hi,

in the docu of getTaskData it says under recode.target: "For survival, you may choose to recode the survival times to 'left', 'right' or 'interval2' censored times using 'lcens', 'rcens' or 'icens', respectively."
This is not consistent with the implementation. If one of these options is chosen, e.g.recode.target = "rcens", an error occurs. Instead, recode.traget = "surv" works. See

Why we use converter/Identity.py and def convert_Identity for the torch.nn.Dropout in https://github.com/NVIDIA-AI-IOT/torch2trt/blob/master/torch2trt/converters/Identity.py
and convert_identity for torch.nn.functional.dropout in
https://github.com/NVIDIA-AI-IOT/torch2trt/blob/master/torch2trt/converters/identity.py

Is it because dropout returns an identical copy of the input tenso

Document the usage of a pretrained model that is available in our model zoo for training against the tiny spacenet quickstart example, to show model improvement through transfer learning via a similar task.

Description

Recently I found that normalized_table_calc function is too slow (more than 30% of the total execution time!!!) and it seems that the reason is the poor performance of numpy.around and built-in round function in scalar mode!!

I think, we should define our custom rounder function, something like this :

def custom_rounder(input_number,digit):
    p =