eval_MR_multisetup.py

import numpy as np
import datetime
import time
from collections import defaultdict
# from . import mask as maskUtils
import copy
import matplotlib.pyplot as plt
import scipy.io as sio

class COCOeval: 
    # Interface for evaluating detection on the Microsoft COCO dataset.
    #
    # The usage for CocoEval is as follows:
    #  cocoGt=..., cocoDt=...       # load dataset and results
    #  E = CocoEval(cocoGt,cocoDt); # initialize CocoEval object
    #  E.params.recThrs = ...;      # set parameters as desired
    #  E.evaluate();                # run per image evaluation
    #  E.accumulate();              # accumulate per image results
    #  E.summarize();               # display summary metrics of results
    # For example usage see evalDemo.m and http://mscoco.org/.
    #
    # The evaluation parameters are as follows (defaults in brackets):
    #  imgIds     - [all] N img ids to use for evaluation
    #  catIds     - [all] K cat ids to use for evaluation
    #  iouThrs    - [.5:.05:.95] T=10 IoU thresholds for evaluation
    #  recThrs    - [0:.01:1] R=101 recall thresholds for evaluation
    #  areaRng    - [...] A=4 object area ranges for evaluation
    #  maxDets    - [1 10 100] M=3 thresholds on max detections per image
    #  iouType    - ['segm'] set iouType to 'segm', 'bbox' or 'keypoints'
    #  iouType replaced the now DEPRECATED useSegm parameter.
    #  useCats    - [1] if true use category labels for evaluation
    # Note: if useCats=0 category labels are ignored as in proposal scoring.
    # Note: multiple areaRngs [Ax2] and maxDets [Mx1] can be specified.
    #
    # evaluate(): evaluates detections on every image and every category and
    # concats the results into the "evalImgs" with fields:
    #  dtIds      - [1xD] id for each of the D detections (dt)
    #  gtIds      - [1xG] id for each of the G ground truths (gt)
    #  dtMatches  - [TxD] matching gt id at each IoU or 0
    #  gtMatches  - [TxG] matching dt id at each IoU or 0
    #  dtScores   - [1xD] confidence of each dt
    #  gtIgnore   - [1xG] ignore flag for each gt
    #  dtIgnore   - [TxD] ignore flag for each dt at each IoU
    #
    # accumulate(): accumulates the per-image, per-category evaluation
    # results in "evalImgs" into the dictionary "eval" with fields:
    #  params     - parameters used for evaluation
    #  date       - date evaluation was performed
    #  counts     - [T,R,K,A,M] parameter dimensions (see above)
    #  precision  - [TxRxKxAxM] precision for every evaluation setting
    #  recall     - [TxKxAxM] max recall for every evaluation setting
    # Note: precision and recall==-1 for settings with no gt objects.
    #
    # See also coco, mask, pycocoDemo, pycocoEvalDemo
    #
    # Microsoft COCO Toolbox.      version 2.0
    # Data, paper, and tutorials available at:  http://mscoco.org/
    # Code written by Piotr Dollar and Tsung-Yi Lin, 2015.
    # Licensed under the Simplified BSD License [see coco/license.txt]
    def __init__(self, cocoGt=None, cocoDt=None, iouType='segm'):
        '''
        Initialize CocoEval using coco APIs for gt and dt
        :param cocoGt: coco object with ground truth annotations
        :param cocoDt: coco object with detection results
        :return: None
        '''
        if not iouType:
            print('iouType not specified. use default iouType segm')
        self.cocoGt   = cocoGt              # ground truth COCO API
        self.cocoDt   = cocoDt              # detections COCO API
        self.params   = {}                  # evaluation parameters
        self.evalImgs = defaultdict(list)   # per-image per-category evaluation results [KxAxI] elements
        self.eval     = {}                  # accumulated evaluation results
        self._gts = defaultdict(list)       # gt for evaluation
        self._dts = defaultdict(list)       # dt for evaluation
        self.params = Params(iouType=iouType) # parameters
        self._paramsEval = {}               # parameters for evaluation
        self.stats = []                     # result summarization
        self.ious = {}                      # ious between all gts and dts
        if not cocoGt is None:
            self.params.imgIds = sorted(cocoGt.getImgIds())
            self.params.catIds = sorted(cocoGt.getCatIds())


    def _prepare(self, id_setup):
        '''
        Prepare ._gts and ._dts for evaluation based on params
        :return: None
        '''
        p = self.params
        if p.useCats:
            gts=self.cocoGt.loadAnns(self.cocoGt.getAnnIds(imgIds=p.imgIds, catIds=p.catIds))
            dts=self.cocoDt.loadAnns(self.cocoDt.getAnnIds(imgIds=p.imgIds, catIds=p.catIds))
        else:
            gts=self.cocoGt.loadAnns(self.cocoGt.getAnnIds(imgIds=p.imgIds))
            dts=self.cocoDt.loadAnns(self.cocoDt.getAnnIds(imgIds=p.imgIds))


        # set ignore flag
        for gt in gts:
            gt['ignore'] = gt['ignore'] if 'ignore' in gt else 0
            gt['ignore'] = 1 if (gt['height'] < self.params.HtRng[id_setup][0] or gt['height'] > self.params.HtRng[id_setup][1]) or \
               ( gt['vis_ratio'] < self.params.VisRng[id_setup][0] or gt['vis_ratio'] > self.params.VisRng[id_setup][1]) else gt['ignore']

        self._gts = defaultdict(list)       # gt for evaluation
        self._dts = defaultdict(list)       # dt for evaluation
        for gt in gts:
            self._gts[gt['image_id'], gt['category_id']].append(gt)
        for dt in dts:
            self._dts[dt['image_id'], dt['category_id']].append(dt)
        self.evalImgs = defaultdict(list)   # per-image per-category evaluation results
        self.eval     = {}                  # accumulated evaluation results

    def evaluate(self, id_setup):
        '''
        Run per image evaluation on given images and store results (a list of dict) in self.evalImgs
        :return: None
        '''
        tic = time.time()
        # print('Running per image evaluation...')
        p = self.params
        # add backward compatibility if useSegm is specified in params
        if not p.useSegm is None:
            p.iouType = 'segm' if p.useSegm == 1 else 'bbox'
            print('useSegm (deprecated) is not None. Running {} evaluation'.format(p.iouType))
        # print('Evaluate annotation type *{}*'.format(p.iouType))
        p.imgIds = list(np.unique(p.imgIds))
        if p.useCats:
            p.catIds = list(np.unique(p.catIds))#[0,1,2,3,4,5]
        p.maxDets = sorted(p.maxDets)#[1000]
        self.params=p

        self._prepare(id_setup)
        # loop through images, area range, max detection number
        catIds = p.catIds if p.useCats else [-1]

        computeIoU = self.computeIoU

        self.ious = {(imgId, catId): computeIoU(imgId, catId) \
                        for imgId in p.imgIds
                        for catId in catIds}

        evaluateImg = self.evaluateImg
        maxDet = p.maxDets[-1]
        HtRng = self.params.HtRng[id_setup]#[[50, 10000000000.0], [50, 10000000000.0], [50, 10000000000.0], [50, 10000000000.0]]
        VisRng = self.params.VisRng[id_setup]#[[0.65, 10000000000.0], [0.9, 10000000000.0], [0.65, 0.9], [0, 0.65]]
        self.evalImgs = [evaluateImg(imgId, catId, HtRng, VisRng, maxDet)
                 for catId in catIds
                 for imgId in p.imgIds
             ]
        self._paramsEval = copy.deepcopy(self.params)
        toc = time.time()
        # print('DONE (t={:0.2f}s).'.format(toc-tic))


    def computeIoU(self, imgId, catId):
        p = self.params
        if p.useCats:
            gt = self._gts[imgId,catId]
            dt = self._dts[imgId,catId]
        else:
            gt = [_ for cId in p.catIds for _ in self._gts[imgId,cId]]
            dt = [_ for cId in p.catIds for _ in self._dts[imgId,cId]]
        if len(gt) == 0 and len(dt) ==0:
            return []
        inds = np.argsort([-d['score'] for d in dt], kind='mergesort')
        dt = [dt[i] for i in inds]
        if len(dt) > p.maxDets[-1]:
            dt=dt[0:p.maxDets[-1]]


        if p.iouType == 'segm':
            g = [g['segmentation'] for g in gt]
            d = [d['segmentation'] for d in dt]
        elif p.iouType == 'bbox':
            g = [g['bbox'] for g in gt]
            d = [d['bbox'] for d in dt]
        else:
            raise Exception('unknown iouType for iou computation')


        # compute iou between each dt and gt region
        iscrowd = [int(o['ignore']) for o in gt]
        ious = self.iou(d,g,iscrowd)
        return ious

    def iou( self, dts, gts, pyiscrowd ):
        dts = np.asarray(dts)
        gts = np.asarray(gts)
        pyiscrowd = np.asarray(pyiscrowd)
        ious = np.zeros((len(dts), len(gts)))
        for j, gt in enumerate(gts):
            gx1 = gt[0]
            gy1 = gt[1]
            gx2 = gt[0] + gt[2]
            gy2 = gt[1] + gt[3]
            garea = gt[2] * gt[3]
            for i, dt in enumerate(dts):
                dx1 = dt[0]
                dy1 = dt[1]
                dx2 = dt[0] + dt[2]
                dy2 = dt[1] + dt[3]
                darea = dt[2] * dt[3]

                unionw = min(dx2,gx2)-max(dx1,gx1)
                if unionw <= 0:
                    continue
                unionh = min(dy2,gy2)-max(dy1,gy1)
                if unionh <= 0:
                    continue
                t = unionw * unionh
                if pyiscrowd[j]:
                    unionarea = darea
                else:
                    unionarea = darea + garea - t

                ious[i, j] = float(t)/unionarea
        return ious

    def evaluateImg(self, imgId, catId, hRng, vRng, maxDet):
        '''
        perform evaluation for single category and image
        :return: dict (single image results)
        '''
        # if imgId==273:
        #     pass
        p = self.params
        if p.useCats:
            gt = self._gts[imgId,catId]
            dt = self._dts[imgId,catId]
        else:
            gt = [_ for cId in p.catIds for _ in self._gts[imgId,cId]]
            dt = [_ for cId in p.catIds for _ in self._dts[imgId,cId]]
        if len(gt) == 0 and len(dt) ==0:
            return None

        for g in gt:
            if g['ignore']:
                g['_ignore'] = 1
            else:
                g['_ignore'] = 0
        # sort dt highest score first, sort gt ignore last
        gtind = np.argsort([g['_ignore'] for g in gt], kind='mergesort')
        gt = [gt[i] for i in gtind]
        dtind = np.argsort([-d['score'] for d in dt], kind='mergesort')
        # dtind = np.argsort([-d['score'] for d in dt])
        dt = [dt[i] for i in dtind[0:maxDet]]
        # exclude dt out of height range
        # dt = [d for d in dt if d['height'] >= hRng[0] / self.params.expFilter and d['height'] < hRng[1] * self.params.expFilter]
        # dtind = np.array([int(d['id'] - dt[0]['id']) for d in dt])
        # dtind = [i for i in range(len(dt)) if dt[i]['height'] >= hRng[0] / self.params.expFilter and dt[i]['height'] < hRng[1] * self.params.expFilter]
        # dt = [d for d in dt if d['height'] >= hRng[0] / self.params.expFilter and d['height'] < hRng[1] * self.params.expFilter]
        dtind = [i for i in range(len(dt)) if
                 dt[i]['bbox'][-1] >= hRng[0] / self.params.expFilter and dt[i]['bbox'][-1] < hRng[
                     1] * self.params.expFilter]
        dt = [d for d in dt if
              d['bbox'][-1] >= hRng[0] / self.params.expFilter and d['bbox'][-1] < hRng[1] * self.params.expFilter]
        # if np.max(dtind)>1000:
        #     pass

        # load computed ious
        if len(dtind) > 0:
            ious = self.ious[imgId, catId][dtind, :] if len(self.ious[imgId, catId]) > 0 else self.ious[imgId, catId]
            ious = ious[:, gtind]
        else:
            ious = []

        T = len(p.iouThrs)
        G = len(gt)
        D = len(dt)
        gtm  = np.zeros((T,G))
        dtm  = np.zeros((T,D))
        gtIg = np.array([g['_ignore'] for g in gt])
        dtIg = np.zeros((T,D))
        if not len(ious)==0:
            for tind, t in enumerate(p.iouThrs):
                for dind, d in enumerate(dt):
                    # information about best match so far (m=-1 -> unmatched)
                    iou = min([t,1-1e-10])
                    bstOa = iou
                    bstg = -2
                    bstm = -2
                    for gind, g in enumerate(gt):
                        m = gtm[tind,gind]
                        # if this gt already matched, and not a crowd, continue
                        if m>0:
                            continue
                        # if dt matched to reg gt, and on ignore gt, stop
                        if bstm!=-2 and gtIg[gind] == 1:
                            break
                        # continue to next gt unless better match made
                        if ious[dind,gind] < bstOa:
                            continue
                        # if match successful and best so far, store appropriately
                        bstOa=ious[dind,gind]
                        bstg = gind
                        if gtIg[gind] == 0:
                            bstm = 1
                        else:
                            bstm = -1

                    # if match made store id of match for both dt and gt
                    if bstg ==-2:
                        continue
                    dtIg[tind,dind] = gtIg[bstg]
                    dtm[tind,dind]  = gt[bstg]['id']
                    if bstm == 1:
                        gtm[tind,bstg]     = d['id']

        # store results for given image and category
        return {
                'image_id':     imgId,
                'category_id':  catId,
                'hRng':         hRng,
                'vRng':         vRng,
                'maxDet':       maxDet,
                'dtIds':        [d['id'] for d in dt],
                'gtIds':        [g['id'] for g in gt],
                'dtMatches':    dtm,
                'gtMatches':    gtm,
                'dtScores':     [d['score'] for d in dt],
                'gtIgnore':     gtIg,
                'dtIgnore':     dtIg,
            }

    def accumulate(self, p = None):
        '''
        Accumulate per image evaluation results and store the result in self.eval
        :param p: input params for evaluation
        :return: None
        '''
        # print('Accumulating evaluation results...')
        tic = time.time()
        if not self.evalImgs:
            print('Please run evaluate() first')
        # allows input customized parameters
        if p is None:
            p = self.params
        p.catIds = p.catIds if p.useCats == 1 else [-1]
        T           = len(p.iouThrs)
        R           = len(p.fppiThrs)
        K           = len(p.catIds) if p.useCats else 1
        M           = len(p.maxDets)
        ys   = -np.ones((T,R,K,M)) # -1 for the precision of absent categories


        # create dictionary for future indexing
        _pe = self._paramsEval
        catIds = [1] #_pe.catIds if _pe.useCats else [-1]
        setK = set(catIds)
        setM = set(_pe.maxDets)
        setI = set(_pe.imgIds)
        # get inds to evaluate
        k_list = [n for n, k in enumerate(p.catIds)  if k in setK]

        m_list = [m for n, m in enumerate(p.maxDets) if m in setM]
        i_list = [n for n, i in enumerate(p.imgIds)  if i in setI]
        I0 = len(_pe.imgIds)

        # retrieve E at each category, area range, and max number of detections
        for k, k0 in enumerate(k_list):
            Nk = k0*I0
            for m, maxDet in enumerate(m_list):
                E = [self.evalImgs[Nk + i] for i in i_list]
                E = [e for e in E if not e is None]
                if len(E) == 0:
                    continue

                dtScores = np.concatenate([e['dtScores'][0:maxDet] for e in E])

                # different sorting method generates slightly different results.
                # mergesort is used to be consistent as Matlab implementation.

                inds = np.argsort(-dtScores, kind='mergesort')

                dtm = np.concatenate([e['dtMatches'][:, 0:maxDet] for e in E], axis=1)[:, inds]
                dtIg = np.concatenate([e['dtIgnore'][:, 0:maxDet] for e in E], axis=1)[:, inds]
                gtIg = np.concatenate([e['gtIgnore'] for e in E])
                npig = np.count_nonzero(gtIg == 0)
                if npig == 0:
                    continue
                tps = np.logical_and(dtm, np.logical_not(dtIg))
                fps = np.logical_and(np.logical_not(dtm), np.logical_not(dtIg))
                inds = np.where(dtIg==0)[1]
                tps = tps[:,inds]
                fps = fps[:,inds]

                tp_sum = np.cumsum(tps, axis=1).astype(dtype=np.float)
                fp_sum = np.cumsum(fps, axis=1).astype(dtype=np.float)
                for t, (tp, fp) in enumerate(zip(tp_sum, fp_sum)):
                    tp = np.array(tp)
                    fppi = np.array(fp)/I0
                    nd = len(tp)
                    recall = tp / npig
                    q = np.zeros((R,))

                    # numpy is slow without cython optimization for accessing elements
                    # use python array gets significant speed improvement
                    recall = recall.tolist()
                    q = q.tolist()

                    for i in range(nd - 1, 0, -1):
                        if recall[i] < recall[i - 1]:
                            recall[i - 1] = recall[i]

                    inds = np.searchsorted(fppi, p.fppiThrs, side='right') - 1
                    try:
                        for ri, pi in enumerate(inds):
                            q[ri] = recall[pi]
                    except:
                        pass
                    ys[t,:,k,m] = np.array(q)
        self.eval = {
            'params': p,
            'counts': [T, R, K, M],
            'date': datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
            'TP':   ys,
        }
        toc = time.time()
        # print('DONE (t={:0.2f}s).'.format( toc-tic))

    def summarize(self,id_setup, res_file):
        '''
        Compute and display summary metrics for evaluation results.
        Note this functin can *only* be applied on the default parameter setting
        '''
        def _summarize(iouThr=None, maxDets=100 ):
            p = self.params
            iStr = ' {:<18} {} @ {:<18} [ IoU={:<9} | height={:>6s} | visibility={:>6s} ] = {:0.2f}%'
            titleStr = 'Average Miss Rate'
            typeStr = '(MR)'
            setupStr = p.SetupLbl[id_setup]
            iouStr = '{:0.2f}:{:0.2f}'.format(p.iouThrs[0], p.iouThrs[-1]) \
                if iouThr is None else '{:0.2f}'.format(iouThr)
            heightStr = '[{:0.0f}:{:0.0f}]'.format(p.HtRng[id_setup][0], p.HtRng[id_setup][1])
            occlStr = '[{:0.2f}:{:0.2f}]'.format(p.VisRng[id_setup][0], p.VisRng[id_setup][1])

            mind = [i for i, mDet in enumerate(p.maxDets) if mDet == maxDets]

            # dimension of precision: [TxRxKxAxM]
            s = self.eval['TP']
            # IoU
            if iouThr is not None:
                t = np.where(iouThr == p.iouThrs)[0]
                s = s[t]
            mrs = 1-s[:,:,:,mind]

            if len(mrs[mrs<2])==0:
                mean_s = -1
            else:
                mean_s = np.log(mrs[mrs<2])
                mean_s = np.mean(mean_s)
                mean_s = np.exp(mean_s)
            print(iStr.format(titleStr, typeStr,setupStr, iouStr, heightStr, occlStr, mean_s*100))
            # res_file.write(iStr.format(titleStr, typeStr,setupStr, iouStr, heightStr, occlStr, mean_s*100))
            res_file.write(str(mean_s * 100))
            res_file.write('\n')
            return mean_s

        if not self.eval:
            raise Exception('Please run accumulate() first')
        _summarize(iouThr=.5,maxDets=1000)

    def summarize_nofile(self,id_setup):
        '''
        Compute and display summary metrics for evaluation results.
        Note this functin can *only* be applied on the default parameter setting
        '''
        def _summarize(iouThr=None, maxDets=100 ):
            p = self.params

            mind = [i for i, mDet in enumerate(p.maxDets) if mDet == maxDets]

            # dimension of precision: [TxRxKxAxM]
            s = self.eval['TP']
            # IoU
            if iouThr is not None:
                t = np.where(iouThr == p.iouThrs)[0]
                s = s[t]
            mrs = 1-s[:,:,:,mind]

            if len(mrs[mrs<2])==0:
                mean_s = -1
            else:
                mean_s = np.log(mrs[mrs<2])
                mean_s = np.mean(mean_s)
                mean_s = np.exp(mean_s)
            return mean_s

        if not self.eval:
            raise Exception('Please run accumulate() first')
        return _summarize(iouThr=.5, maxDets=1000)

    def __str__(self):
        self.summarize()

class Params:
    '''
    Params for coco evaluation api
    '''
    def setDetParams(self):
        self.imgIds = []
        self.catIds = []
        # np.arange causes trouble.  the data point on arange is slightly larger than the true value

        self.recThrs = np.linspace(.0, 1.00, int(np.round((1.00 - .0) / .01)) + 1, endpoint=True)
        self.fppiThrs = np.array([0.0100,    0.0178,    0.0316,    0.0562,    0.1000,    0.1778,    0.3162,    0.5623,    1.0000])
        self.maxDets = [1000]
        self.expFilter = 1.25
        self.useCats = 1

        self.iouThrs = np.array([0.5])  # np.linspace(.5, 0.95, np.round((0.95 - .5) / .05) + 1, endpoint=True)

        # self.HtRng = [[50, 1e5 ** 2], [50,75], [50, 1e5 ** 2], [20, 1e5 ** 2]]
        # self.VisRng = [[0.65, 1e5 ** 2], [0.65, 1e5 ** 2], [0.2,0.65], [0.2, 1e5 ** 2]]
        # self.SetupLbl = ['Reasonable', 'Reasonable_small','Reasonable_occ=heavy', 'All']

        # self.HtRng = [[50, 1e5 ** 2], [50, 75], [75, 100], [100, 1e5 ** 2]]
        # self.VisRng = [[0.65, 1e5 ** 2], [0.65, 1e5 ** 2], [0.65, 1e5 ** 2], [0.65, 1e5 ** 2]]
        # self.SetupLbl = ['Reasonable', 'small', 'middle', 'large']

        self.HtRng = [[50, 1e5 ** 2], [50, 1e5 ** 2], [50, 1e5 ** 2], [50, 1e5 ** 2]]
        self.VisRng = [[0.65, 1e5 ** 2], [0.9, 1e5 ** 2], [0.65, 0.9], [0, 0.65]]
        self.SetupLbl = ['Reasonable', 'bare', 'partial', 'heavy']


    def __init__(self, iouType='segm'):
        if iouType == 'segm' or iouType == 'bbox':
            self.setDetParams()
        else:
            raise Exception('iouType not supported')
        self.iouType = iouType
        # useSegm is deprecated
        self.useSegm = None