live-wire

from graphviz import Digraph
import torch
from torch.autograd import Variable, Function

def iter_graph(root, callback):
    queue = [root]
    seen = set()
    while queue:
        fn = queue.pop()
        if fn in seen:

live-wire

import re
import sys


stringtoreplace = "<toc>"

def generateTOC(filename):
   contents = []
   with open(filename, "r") as ins:
      for line in ins:

live-wire

live-wire

MNIST challenge creation for EvalAI

A tutorial on how I created the mnist-challenge

I started with going through this documentation about challenge creation. This involves creation of a yaml configuration file for the challenge.

Before we dive into the configuration, we need to establish a few things about the platform. Each challenge is split into phases decided by the host (us in this scenario). The host can have different dataset splits for different challenge phases. The host can set the visibility of the challenge phases and also of the leaderboards to HOST, OWNER & HOST or PUBLIC. The number and types of columns in the leaderboard is also configurable.

Configuration

Let me use the configuration I created for the challenge and go through it line by line:

live-wire

"""
Input: GT JSON file, Pred JSON file, Phase-CodeName

Hardcoded path of a split-JSON file which has the following structure
Split JSON File Structure - 
{
    split1 : [list of qids]
    split2 : [list of qids]
    split3 : [list of qids]
    split4 : [list of qids]