Lines Matching defs:Model
21 letter_recog.py [--model <model>]
23 [--load <model fn>] [--save <model fn>]
41 self.model.load(fn)
43 self.model.save(fn)
61 self.model = cv2.RTrees()
68 self.model.train(samples, cv2.CV_ROW_SAMPLE, responses, varType = var_types, params = params)
71 return np.float32( [self.model.predict(s) for s in samples] )
76 self.model = cv2.KNearest()
79 self.model.train(samples, responses)
82 retval, results, neigh_resp, dists = self.model.find_nearest(samples, k = 10)
88 self.model = cv2.Boost()
97 self.model.train(new_samples, cv2.CV_ROW_SAMPLE, new_responses, varType = var_types, params=params)
101 pred = np.array( [self.model.predict(s, returnSum = True) for s in new_samples] )
108 self.model = cv2.SVM()
114 self.model.train(samples, responses, params = params)
117 return self.model.predict_all(samples).ravel()
122 self.model = cv2.ANN_MLP()
129 self.model.create(layer_sizes)
136 self.model.train(samples, np.float32(new_responses), None, params = params)
139 ret, resp = self.model.predict(samples)
153 args, dummy = getopt.getopt(sys.argv[1:], '', ['model=', 'data=', 'load=', 'save='])
155 args.setdefault('--model', 'rtrees')
160 Model = models[args['--model']]
161 model = Model()
163 train_n = int(len(samples)*model.train_ratio)
166 print 'loading model from %s ...' % fn
167 model.load(fn)
169 print 'training %s ...' % Model.__name__
170 model.train(samples[:train_n], responses[:train_n])
173 train_rate = np.mean(model.predict(samples[:train_n]) == responses[:train_n])
174 test_rate = np.mean(model.predict(samples[train_n:]) == responses[train_n:])
180 print 'saving model to %s ...' % fn
181 model.save(fn)
