1#!/usr/bin/env python 2 3''' 4Digit recognition adjustment. 5Grid search is used to find the best parameters for SVM and KNearest classifiers. 6SVM adjustment follows the guidelines given in 7http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf 8 9Threading or cloud computing (with http://www.picloud.com/)) may be used 10to speedup the computation. 11 12Usage: 13 digits_adjust.py [--model {svm|knearest}] [--cloud] [--env <PiCloud environment>] 14 15 --model {svm|knearest} - select the classifier (SVM is the default) 16 --cloud - use PiCloud computing platform 17 --env - cloud environment name 18 19''' 20# TODO cloud env setup tutorial 21 22import numpy as np 23import cv2 24from multiprocessing.pool import ThreadPool 25 26from digits import * 27 28try: 29 import cloud 30 have_cloud = True 31except ImportError: 32 have_cloud = False 33 34 35 36def cross_validate(model_class, params, samples, labels, kfold = 3, pool = None): 37 n = len(samples) 38 folds = np.array_split(np.arange(n), kfold) 39 def f(i): 40 model = model_class(**params) 41 test_idx = folds[i] 42 train_idx = list(folds) 43 train_idx.pop(i) 44 train_idx = np.hstack(train_idx) 45 train_samples, train_labels = samples[train_idx], labels[train_idx] 46 test_samples, test_labels = samples[test_idx], labels[test_idx] 47 model.train(train_samples, train_labels) 48 resp = model.predict(test_samples) 49 score = (resp != test_labels).mean() 50 print ".", 51 return score 52 if pool is None: 53 scores = map(f, xrange(kfold)) 54 else: 55 scores = pool.map(f, xrange(kfold)) 56 return np.mean(scores) 57 58 59class App(object): 60 def __init__(self, usecloud=False, cloud_env=''): 61 if usecloud and not have_cloud: 62 print 'warning: cloud module is not installed, running locally' 63 usecloud = False 64 self.usecloud = usecloud 65 self.cloud_env = cloud_env 66 67 if self.usecloud: 68 print 'uploading dataset to cloud...' 69 cloud.files.put(DIGITS_FN) 70 self.preprocess_job = cloud.call(self.preprocess, _env=self.cloud_env) 71 else: 72 self._samples, self._labels = self.preprocess() 73 74 def preprocess(self): 75 if self.usecloud: 76 cloud.files.get(DIGITS_FN) 77 digits, labels = load_digits(DIGITS_FN) 78 shuffle = np.random.permutation(len(digits)) 79 digits, labels = digits[shuffle], labels[shuffle] 80 digits2 = map(deskew, digits) 81 samples = preprocess_hog(digits2) 82 return samples, labels 83 84 def get_dataset(self): 85 if self.usecloud: 86 return cloud.result(self.preprocess_job) 87 else: 88 return self._samples, self._labels 89 90 def run_jobs(self, f, jobs): 91 if self.usecloud: 92 jids = cloud.map(f, jobs, _env=self.cloud_env, _profile=True, _depends_on=self.preprocess_job) 93 ires = cloud.iresult(jids) 94 else: 95 pool = ThreadPool(processes=cv2.getNumberOfCPUs()) 96 ires = pool.imap_unordered(f, jobs) 97 return ires 98 99 def adjust_SVM(self): 100 Cs = np.logspace(0, 10, 15, base=2) 101 gammas = np.logspace(-7, 4, 15, base=2) 102 scores = np.zeros((len(Cs), len(gammas))) 103 scores[:] = np.nan 104 105 print 'adjusting SVM (may take a long time) ...' 106 def f(job): 107 i, j = job 108 samples, labels = self.get_dataset() 109 params = dict(C = Cs[i], gamma=gammas[j]) 110 score = cross_validate(SVM, params, samples, labels) 111 return i, j, score 112 113 ires = self.run_jobs(f, np.ndindex(*scores.shape)) 114 for count, (i, j, score) in enumerate(ires): 115 scores[i, j] = score 116 print '%d / %d (best error: %.2f %%, last: %.2f %%)' % (count+1, scores.size, np.nanmin(scores)*100, score*100) 117 print scores 118 119 print 'writing score table to "svm_scores.npz"' 120 np.savez('svm_scores.npz', scores=scores, Cs=Cs, gammas=gammas) 121 122 i, j = np.unravel_index(scores.argmin(), scores.shape) 123 best_params = dict(C = Cs[i], gamma=gammas[j]) 124 print 'best params:', best_params 125 print 'best error: %.2f %%' % (scores.min()*100) 126 return best_params 127 128 def adjust_KNearest(self): 129 print 'adjusting KNearest ...' 130 def f(k): 131 samples, labels = self.get_dataset() 132 err = cross_validate(KNearest, dict(k=k), samples, labels) 133 return k, err 134 best_err, best_k = np.inf, -1 135 for k, err in self.run_jobs(f, xrange(1, 9)): 136 if err < best_err: 137 best_err, best_k = err, k 138 print 'k = %d, error: %.2f %%' % (k, err*100) 139 best_params = dict(k=best_k) 140 print 'best params:', best_params, 'err: %.2f' % (best_err*100) 141 return best_params 142 143 144if __name__ == '__main__': 145 import getopt 146 import sys 147 148 print __doc__ 149 150 args, _ = getopt.getopt(sys.argv[1:], '', ['model=', 'cloud', 'env=']) 151 args = dict(args) 152 args.setdefault('--model', 'svm') 153 args.setdefault('--env', '') 154 if args['--model'] not in ['svm', 'knearest']: 155 print 'unknown model "%s"' % args['--model'] 156 sys.exit(1) 157 158 t = clock() 159 app = App(usecloud='--cloud' in args, cloud_env = args['--env']) 160 if args['--model'] == 'knearest': 161 app.adjust_KNearest() 162 else: 163 app.adjust_SVM() 164 print 'work time: %f s' % (clock() - t) 165