Result

Instructions

For training the model, use only training set do not use validation and test sets.

The organizers request the team to upload the final/updated trained model, inference code, ReadMe file, and algorithm details on the competition website on or before 10th April. If there is a mismatch between the results uploaded, the trained model submitted and the results obtained by the inference code by the team, then the team will not be allowed to continue the competition. In such a case, the team results will not be displayed on the leaderboard.

Submission of Brief Description of Algorithm
  • Write a maximum of one page description of your proposed method to solve the problem at hand and name the file as description.doc/description.pdf/description.txt/description.latex. Please make sure to add details of any open source or commercially available tool used for OCR or recognition of table structures, etc.
Submission of Results
  • The output of the test set should be a zipped folder such that there is an output json file for each image in the format as shown below:
Example:

For the following test image file:
table

The test json asking questions would look like:
table

Corresponding answer json should look like:
table

Please make sure that the predictions are expected in a similar JSON format such that the key at the first level is the category_id. Within each category is a nested dictionary such that its key is the question_id and corresponding value is the predicted answer. Also, please make sure that the answers to the questions are mapped using the same question ids. Lastly, please ensure that the name of the answer file is exactly the same as the name of the question file. If the question file is named as test_file_0.json, your answer file should be named as test_file_0.json as well. Put all the files in the folder called ‘answers’, zip it and upload it in the link provided.

Submission of Trained Model
  • Create a zip file of the trained model(s) and upload
Submission of Inference Code
  • Inference code, requirement.txt with software packages required to run the code, ReadMe file with instructions for running the code. Make a zip file and upload it.

Select Team Name

 

Upload Result

 

Upload Inference Code

 

Upload Trained Model

 

Upload Brief Description of Algorithm