#!/usr/bin/env python # Author: Vasil Zlatanov, Nunzio Pucci # EE4 Pattern Recognition coursework # # usage: opt.py [-h] [-t] [-c] [-k] [-m] [-e] [-r] [-a RERANKA] # [-b RERANKB] [-l RERANKL] [-n NEIGHBORS] [-v] # [-s SHOWRANK] [-1] [-2] [-M MULTRANK] [-C] [DATA] # [-K KMEAN] [-A] [-P PCA] import matplotlib.pyplot as plt import sys import os import json import scipy.io from sklearn.neighbors import NearestNeighbors from sklearn.cluster import KMeans from sklearn.decomposition import PCA from sklearn.model_selection import train_test_split from sklearn.metrics import confusion_matrix from sklearn.metrics import accuracy_score import argparse import numpy as np from numpy import genfromtxt from numpy import linalg as LA from timeit import default_timer as timer from scipy.spatial.distance import cdist sys.path.append('lib') from rerank import re_ranking from kmean import create_kmean_clusters import logging from logging import debug from evaluate import test_model from evaluate import draw_results parser = argparse.ArgumentParser() parser.add_argument("-t", "--train", help="Use train data instead of query and gallery", action='store_true') parser.add_argument("-c", "--conf_mat", help="Show visual confusion matrix", action='store_true') parser.add_argument("-k", "--kmean_alt", help="Perform clustering with generalized labels(not actual kmean)", action='store_true') parser.add_argument("-m", "--mahalanobis", help="Perform Mahalanobis Distance metric", action='store_true') parser.add_argument("-e", "--euclidean", help="Use standard euclidean distance", action='store_true') parser.add_argument("-r", "--rerank", help="Use k-reciprocal rernaking", action='store_true') parser.add_argument("-a", "--reranka", help="Parameter k1 for rerank", type=int, default = 9) parser.add_argument("-b", "--rerankb", help="Parameter k2 for rerank", type=int, default = 3) parser.add_argument("-l", "--rerankl", help="Parameter lambda for rerank", type=float, default = 0.3) parser.add_argument("-n", "--neighbors", help="Use customized ranklist size NEIGHBORS", type=int, default = 1) parser.add_argument("-v", "--verbose", help="Use verbose output", action='store_true') parser.add_argument("-s", "--showrank", help="Save ranklist pics id in a txt file for first SHOWRANK queries", type=int, default = 0) parser.add_argument("-1", "--normalise", help="Normalise features", action='store_true') parser.add_argument("-2", "--standardise", help="Standardise features", action='store_true') parser.add_argument("-M", "--multrank", help="Run for different ranklist sizes equal to MULTRANK", type=int, default=1) parser.add_argument("-C", "--comparison", help="Compare baseline and improved metric", action='store_true') parser.add_argument("--data", help="Folder containing data", default='data') parser.add_argument("-K", "--kmean", help="Perform Kmean clustering, KMEAN number of clusters", type=int, default=0) parser.add_argument("-A", "--mAP", help="Display Mean Average Precision", action='store_true') parser.add_argument("-P", "--PCA", help="Perform pca with PCA eigenvectors", type=int, default=50) args = parser.parse_args() if args.verbose: logging.basicConfig(level=logging.DEBUG) def eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args): if args.train: cam = camId[train_idx] cam = cam.reshape((cam.shape[0],1)) labs = labels[train_idx].reshape((labels[train_idx].shape[0],1)) tt = np.hstack((train_idx, cam)) train, test, train_label, test_label = train_test_split(tt, labs, test_size=0.3, random_state=0) del labs del cam train_data = feature_vectors[train[:,0]] test_data = feature_vectors[test[:,0]] train_cam = train[:,1] test_cam = test[:,1] showfiles_train = filelist[train[:,0]] showfiles_test = filelist[train[:,0]] del train del test del tt else: query_idx = query_idx.reshape(query_idx.shape[0]) gallery_idx = gallery_idx.reshape(gallery_idx.shape[0]) camId = camId.reshape(camId.shape[0]) showfiles_train = filelist[gallery_idx] showfiles_test = filelist[query_idx] train_data = feature_vectors[gallery_idx] test_data = feature_vectors[query_idx] train_label = labels[gallery_idx] test_label = labels[query_idx] train_cam = camId[gallery_idx] test_cam = camId[query_idx] train_idx = train_idx.reshape(train_idx.shape[0]) train_model = feature_vectors[train_idx] if(args.PCA): pca=PCA(n_components=args.PCA) #Data variance @100 is 94% train_model=pca.fit_transform(train_model) train_data=pca.transform(train_data) test_data=pca.transform(test_data) if args.mAP: target_pred, mAP = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, train_model, args) return mAP else: target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, train_model, args) target_pred = target_pred.reshape(target_pred.shape[1]) return draw_results(test_label, target_pred) def kopt(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args): axis = 0 search = 0 steps = 0 vertical = True neg = False outofaxis = False start = np.array([1,1]) if args.mAP: args.neighbors = 10 args.train = True args.rerank = True args.reranka = 1 args.rerankb = 1 opt = np.array([1,1]) checktab = np.zeros((100,100)) checktab[1][1]=1 max_acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args) print('origin') print('vertical') while steps<3: steps+=1 while axis<4: axis+=1 p = start[0] q = start[1] while search <5: search+=1 if vertical: if neg: p = start[0] - 2*search if p < 1: p = 1 search = 5 outofaxis = True else: p = search*2 + start[0] args.reranka = p if not outofaxis: if checktab[p][q] == 0: checktab[p][q] = 1 print('p:',p,' q:',q) acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args) if acc > max_acc: print('new p:',p, ' for accuracy:', acc) max_acc=acc opt[0] = p start[0] = p axis=0 steps=0 search=6 else: if neg: q = start[1] - 2*search if q < 1: q = 1 search = 5 outofaxis = True else: q = search*2 + start[1] args.rerankb = q if not outofaxis: if checktab[p][q] == 0: checktab[p][q]=1 print('p:',p,' q:',q) acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args) if acc > max_acc: print('new q:',q, ' for accuracy:', acc) max_acc=acc opt[1] = q start[1] = q axis=0 steps=0 search=6 if search==5: outofaxis = False vertical = not vertical print('vertical:',vertical) search=0 if axis==2 or axis == 4: neg = not neg axis=0 start[0]+=2 start[1]+=2 p=start[0] q=start[1] args.reranka = start[0] args.rerankb = start[1] print('p:',p,' q:',q) acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args) if acc > max_acc: print('new p:',p,'new q:',q, ' for accuracy:', acc) max_acc=acc opt[0] = start[0] opt[1] = start[1] steps=0 vertical=True print('Maximum Accuracy:',max_acc,' found at p:',opt[0],'|q:',opt[1]) return max_acc, opt def main(): mat = scipy.io.loadmat(os.path.join(args.data,'cuhk03_new_protocol_config_labeled.mat')) camId = mat['camId'] filelist = mat['filelist'] labels = mat['labels'] gallery_idx = mat['gallery_idx'] - 1 query_idx = mat['query_idx'] - 1 train_idx = mat['train_idx'] - 1 with open(os.path.join(args.data,'feature_data.json'), 'r') as read_file: feature_vectors = np.array(json.load(read_file)) l=0 max_acc = np.zeros(11) opt = np.zeros((11,2)) while l < 11: args.rerankl = l/10 print('testing for lambda:',args.rerankl) max_acc[l], opt[l] = kopt(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args) l +=1 print('Max accuracy:',np.max(max_acc),' at p:',opt[np.argmax(max_acc)][0], '| q:',opt[np.argmax(max_acc)][1],'| lambda:',np.argmax(max_acc)/10) if __name__ == "__main__": main()