cocoEval summarize()返回所有mAP -1

Question

我创建了一个带有注释的json，并执行以下代码：

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()

但结果如下：

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

为什么每个mAP都返回-1？

我不知道为什么返回这些结果，我认为两个json都是正确的。

我不知道为什么返回这些结果，我认为两个json都是正确的。

我不知道为什么返回这些结果，我认为两个json都是正确的。

Answer 1

你必须注意不同的事情：

• 来自ground truth json的images->id和类别映射中的image_id之间的映射

之间的映射

基本事实json示例

{
    "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}]