GPhilo

@Ezra-Yu my problem with `ClassBalancedDataset` is that it gives no control on what the actual target distribution for classes will be, it just balances the classes so that they're approximately...

Hello, I ran into the same problem. Was there any solution to this?

A quick update since I'm now digging into the library. I see that there is an `idx_dtype` parameter for the constructor of `COO` that -I believe- should force COO to...

I traced the issue to its source and came up with a hack to make this work, should anyone else also run into this problem. Basically, when [this reshape](https://github.com/pydata/sparse/blob/30b7172b16a6b333cdda5afc8266e3c1ae067d26/sparse/_coo/core.py#L692) is...

Ah, I see now that there is already a PR for a fix: https://github.com/Anaconda-Platform/nb_conda/pull/75

Did any of you ever get any further info about this? I also noticed tflite seems to be running on a single core..

@salpert-humane I faced the same issue and took inspiration from the [coco TFRecord creation tool here](https://github.com/tensorflow/models/blob/4bd2888b8d2b0015a8fd28c8b9d3d3f275fd55ff/research/object_detection/dataset_tools/create_coco_tf_record.py#L239). @sandhyacs Could you clarify a few things about the keypoints detection framework? As far...

For the record, I clarified those points myself. It is indeed as I described in my previous comment, I am currently training a model with two different keypoint detection tasks...

Hey! I'll try to summarize what I had to do in a more-or-less concise way, it's not very complex but it's a few steps. ## Premise I'll describe the use-case...

@s-nesterov Glad it helps :) I'm not sure whether just using the script you linked works, I guess if you have annotations in the same format used in the COCO...