Pengyu Wang

When training the VGNN, in the attention module we multiply two sparse matrices, edge_e and data, together to produce h_prime. Then the code verifies that whether h_prime contains NaN, which...

In the `process_patient(infile)` function of _preprocess_mimic.py_ file, the below code segment declared two dictionary for storing patient_ids and relevant encounter information ```patient_dict_sorted = {} for patient_id, time_enc_tuples in patient_dict.items(): patient_dict_sorted[patient_id]...

phase 4 correction

2

The popq %rax in the farm does not necessarily require 58 (the corresponding machine code) to be at the rightmost position of the instruciton. It works even if it is...

Customized optimizer

1

## Feature Support for customized optimizers during training allows for greater flexibility in training models. Some frameworks in WSI tasks consist of multiple networks. Right now, we can only build...

First of all, thank you for your work. I was checking the code after reading the paper and have some doubts regarding the implementation. 1. The paper said that all...

feat: replace hardcoded temp directory paths

2

Please briefly answer these questions: * what problem are you trying to solve? (or if there's no problem, what's the motivation for this change?) Fixes #933 * what changes does...

Add exponential histogram one-liner print

8

#### Description This PR fixes #10463 by adding a one-liner debug printer support for exponential bucket. It also adds unit tests for the printing. #### Link to tracking issue Fixes...