aimbrain / vqa-project

Code for our paper: Learning Conditioned Graph Structures for Interpretable Visual Question Answering
Apache License 2.0
148 stars 35 forks source link

Test error #10

Open jungjun9150 opened 5 years ago

jungjun9150 commented 5 years ago

Traceback (most recent call last): File "/media/jungjunkim/rest/VQA-Evaluation/PythonEvaluationTools/vqaEvalDemo.py", line 35, in vqaRes = vqa.loadRes(resFile, quesFile) I run the vqa evaluation code as you mentioned last. but result.json file is different from v2 dataset. so I got the result the below.

File "/media/jungjunkim/rest/VQA-Evaluation/PythonEvaluationTools/vqa.py", line 165, in loadRes 'Results do not correspond to current VQA set. Either the results do not have predictions for all question ids in annotation file or there is at least one question id that does not belong to the question ids in the annotation file.' AssertionError: Results do not correspond to current VQA set. Either the results do not have predictions for all question ids in annotation file or there is at least one question id that does not belong to the question ids in the annotation file.

as the result of analyzing the json file between gt and predictions, question id is different with gt. could you tell me how to test json file?