行人檢測一般用FPPI而不是mAP作爲評估指標,但是網上找了好久都沒找到Python版本的代碼,原來FPPI官方的代碼是matlab的,這裏記錄一下用官方的代碼來繪製FPPI曲線有哪些需要注意的
有兩個方法:
- 用matlab的evaluateDetectionMissRate(建議用這個)
- 用官方的工具包(有一些參數我還沒弄懂,歡迎清楚的小夥伴來填坑)
1. matlab的evaluateDetectionMissRate
感謝這篇文章提供思路:FPPI曲線繪製記錄
matlab官方文檔地址:evaluateDetectionMissRate
測試數據下載地址:matlab繪製FPPI測試數據
load fppi.mat
[am, fppi, missRate] = evaluateDetectionMissRate(results, a);
%%
% Plot log average miss rate - FPPI.
figure
loglog(fppi, missRate);
grid on
title(sprintf('log Average Miss Rate = %.5f',am))
成功繪製後圖片長這個樣子
如果要改成自己數據的話:
預測結果的格式(即代碼中的result):
- 第一列爲[x, y, width, height]
- 第二列爲預測的分數
- 每一行中,第一列和第二列的物體數量要一樣,例如第一列是6個物體,那他的shape爲6*4,那麼第二列也要是6個分數,shape爲1*4(不懂的話可以打開
fppi.mat
看下)
label的格式(即代碼中的a,名字我隨便取的哈哈哈):
- 第一列爲[x, y, width, height]
- 如果有多個物體的話,就用分號
;
隔開 - 預測結果和label的每一行都是指一張圖片,所以兩者的順序要對應上
詳情可以matlab源碼中的註釋:
function [logAverageMissRate, fppi, missRate] = evaluateDetectionMissRate(...
detectionResults, groundTruthData, varargin)
%evaluateDetectionMissRate Evaluate the miss rate metric for object detection.
% logAverageMissRate = evaluateDetectionMissRate(detectionResults,
% groundTruthData) returns log-average miss rate to measure the detection
% performance. For a multi-class detector, logAverageMissRate is a vector
% of log-average miss rates for each object class. The class order
% follows the same column order as the groundTruthData table.
%
% Inputs:
% -------
% detectionResults - a table that has two columns for single-class
% detector, or three columns for multi-class
% detector. The first column contains M-by-4 matrices
% of [x, y, width, height] bounding boxes specifying
% object locations. The second column contains scores
% for each detection. For multi-class detector, the
% third column contains the predicted label for each
% detection. The label must be categorical type
% defined by the variable names of groundTruthData
% table.
%
% groundTruthData - a table that has one column for single-class, or
% multiple columns for multi-class. Each column
% contains M-by-4 matrices of [x, y, width, height]
% bounding boxes specifying object locations. The
% column name specifies the class label.
%
% [..., fppi, missRate] = evaluateDetectionMissRate(...) returns data
% points for plotting the log-miss-rate/false-positives-per-image(FPPI)
% curve. You can visualize the performance curve using loglog(fppi,missRate).
% For multi-class detector, recall and precision are cell arrays, where
% each cell contains the data points for each object class.
%
% [...] = evaluateDetectionMissRate(..., threshold) specifies the
% overlap threshold for assigning a detection to a ground truth box. The
% overlap ratio is computed as the intersection over union. The default
% value is 0.5.
%
% Example : Evaluate stop sign detector
% -------------------------------------
% % Load the ground truth table
% load('stopSignsAndCars.mat')
% stopSigns = stopSignsAndCars(:, 1:2);
% stopSigns.imageFilename = fullfile(toolboxdir('vision'),'visiondata', ...
% stopSigns.imageFilename);
%
% % Train an ACF based detector
% detector = trainACFObjectDetector(stopSigns,'NegativeSamplesFactor',2);
%
% % Create a struct array to store the results
% numImages = height(stopSigns);
% results(numImages) = struct('Boxes', [], 'Scores', []);
%
% % Run the detector on the training images
% for i = 1 : numImages
% I = imread(stopSigns.imageFilename{i});
% [bboxes, scores] = detect(detector, I);
% results(i).Boxes = bboxes;
% results(i).Scores = scores;
% end
%
% results = struct2table(results);
%
% % Evaluate the results against the ground truth data
% [am, fppi, missRate] = evaluateDetectionMissRate(results, stopSigns(:, 2));
%
% % Plot log-miss-rate/FPPI curve
% figure
% loglog(fppi, missRate);
% grid on
% title(sprintf('log Average Miss Rate = %.1f', am))
%
% See also evaluateDetectionPrecision, acfObjectDetector,
% rcnnObjectDetector, trainACFObjectDetector, trainRCNNObjectDetector.
% Copyright 2016 The MathWorks, Inc.
%
% References
% ----------
% [1] C. D. Manning, P. Raghavan, and H. Schutze. An Introduction to
% Information Retrieval. Cambridge University Press, 2008.
%
% [2] D. Hoiem, Y. Chodpathumwan, and Q. Dai. Diagnosing error in
% object detectors. In Proc. ECCV, 2012.
%
% [3] Dollar, Piotr, et al. "Pedestrian Detection: An Evaluation of the
% State of the Art." Pattern Analysis and Machine Intelligence, IEEE
% Transactions on 34.4 (2012): 743 - 761.
2. 用官方的工具包
非常感謝這篇文章:Caltech評估方法
評估的方法按照上面那篇文章可以跑通代碼,需要注意的是:
- 要下載annotations文件,並解壓到
../code3.2.1/data-USA
中 - 在此處下載別人預測的結果,並放在
../code3.2.1/data-USA/res
中(res文件夾需要自己你新建)
文件放置如圖所示:
annotations文件內如圖所示:
res文件內如圖所示(ABC是我自己的算法名字):
3. 修改dbEval.m
中的algs
變量(在第57行),保留要你對比的算法,他的的註釋掉(名字要與你res
文件夾中的算法名字相同)。同時,在最後面加上你自己算法的名字,前面的布爾變量表示是否將每個box的高度調整爲100/128,clrs
表示顏色,'-'
表示線條類型
4. 然後運行dbEval.m
即可。圖會閃一下,因爲最終圖片會保存到pdf裏面,所以需要安裝Ghostscript
和pdfcrop
。當然也可以在savefig(fName1,1,'pdf','-r300','-fonts'); close(1); f1=[fName1 '.pdf'];
設一個斷點,然後手動保存
5. 自己的算法一定要放在前面,不然繪圖的時候會顯示不出來,這個坑以後再填
6. 自己的數據格式摹仿別人的預測就好了,第一列是圖片id,然後是xmin、ymin、w、h,最後不知道是什麼待填坑