Evan Racah

Hey, @ilee300a, this didn't quite make it into v0.11, but we'll do a hotfix this week and add it!

Yes. This is a strange issue that @valiantljk and I were dealing with. I suspect it's some issue with PYTHONPATH and **init**.py Let me look into it

I believe so. For python at least. If you can get a pyspark notebook set up then you can do it. All you need is the h5spark python module to...

Yeah interesting. I think we could do something like sort the file sizes and then progressively assign the next biggest to the partition with the smallest current load. Sort of...

Hmmm interesting question. I believe I computed them using a metadata file and not the HDF5 files. The code I used for that is here: https://github.com/eracah/hur-detect/blob/master/notebooks/load_data/event_counter.ipynb

Lemme see if I can find that metadata file

Also, sorry for the late response and thanks for your interest! I apologize for the messy code and my fuzzy memory of this project! Let me know if you are...

Hi Zihan, That is the correct filter_list. Sorry about the keras code. It is not very readable due to the over-modularizing of everything. Some day I should rewrite a pytorch...

Hi Zihan, So: batch_size, num_boxes, box_dimensionality = [4, 15, 5] So it's supposed to split the last dimension into 3 parts: (y_true_x, y_true_y), (y_true_w, y_true_h), y_true_obj_y_true_cls I think potentially tf.split...

I think `compute_loss` is supposed to be this one: https://github.com/eracah/hur-detect/blob/e597729d9c620cde3c197af20ec3cda1efcfbbf5/dotpy_src/losses/ssd/ssd.py#L29