cocoEval summarize() return all mAP -1 - tensorflow2.0

Question

I create a json with annotations and execute the following code:
import matplotlib.pyplot as plt
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
import numpy as np
import skimage.io as io
import pylab
import json
pylab.rcParams['figure.figsize'] = (10.0, 8.0)
annType = ['segm','bbox','keypoints']
annType = annType[1] #specify type here
prefix = 'person_keypoints' if annType=='keypoints' else 'instances'
print ('Running demo for *%s* results.'%(annType))
# use the valadation labelme file
annFile = '/content/json_moded.json'
cocoGt=COCO(annFile)
#initialize COCO detections api
# use the generated results
resFile = '/content/test_data_normal.json'
cocoDt=cocoGt.loadRes(resFile)
'''
dts = json.load(open(resFile,'r'))
imgIds = [imid['image_id'] for imid in dts]
imgIds = sorted(list(set(imgIds)))
'''
imgIds=sorted(cocoGt.getImgIds())
'''
imgIds=sorted(cocoGt.getImgIds())
imgIds=imgIds[0:24]
imgId = imgIds[np.random.randint(24)]
'''
# running box evaluation
cocoEval = COCOeval(cocoGt,cocoDt,annType)
cocoEval.params.imgIds = imgIds
'''
cocoEval.params.catIds = [3] # 1 stands for the 'person' class, you can increase or decrease the category as needed
'''
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
but the results are the following:
Running demo for *bbox* results.
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
Loading and preparing results...
DONE (t=0.00s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=0.11s).
Accumulating evaluation results...
DONE (t=0.04s).
Average Precision (AP) #[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000
Average Precision (AP) #[ IoU=0.50 | area= all | maxDets=100 ] = -1.000
Average Precision (AP) #[ IoU=0.75 | area= all | maxDets=100 ] = -1.000
Average Precision (AP) #[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Precision (AP) #[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
Average Precision (AP) #[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
Average Recall (AR) #[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = -1.000
Average Recall (AR) #[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = -1.000
Average Recall (AR) #[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000
Average Recall (AR) #[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Recall (AR) #[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
Average Recall (AR) #[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
why every mAP return -1?
I dont know why return these result, i think that both json are corrects.
I dont know why return these result, i think that both json are corrects.
I dont know why return these result, i think that both json are corrects.

Answer 1

You have to pay attention to different things:
the mapping between images->id from ground truth json and image_id in prediction.json
the mapping between category
Ground truth json example
{
"info": {
"year": "2021",
"version": "2",
"description": "",
"contributor": "",
"url": "",
"date_created": ""
},
"licenses": [
{
"id": 1,
"url": "https://creativecommons.org/licenses/by/4.0/",
"name": "CC BY 4.0"
}
],
"categories": [
{
"id": 1,
"name": "cat",
"supercategory": "none"
}
],
"images": [
{
"id": 0,
"license": 1,
"file_name": "1.jpg",
"height": 512,
"width": 512,
"date_captured": ""
},
{
"id": 1,
"license": 1,
"file_name": "e.jpg",
"height": 512,
"width": 512,
"date_captured": ""
}
],
"annotations": [
{
"id": 0,
"image_id": 0,
"category_id": 1,
"bbox": [
261,
358,
16,
26
],
"area": 416,
"segmentation": [],
"iscrowd": 0
}
]
}
prediction.json
[{"image_id": 0, "category_id": 1, "bbox": [84.116, 442.13, 43.356, 25.849], "score": 0.87929}]