def mat2png(): path = '/data/detect/VOC/VOCdevkit/VOC2010/trainval' files = os.listdir(path) labels_path = '/data/detect/VOC/VOCdevkit/VOC2010/test22' #Seglabels' #os.path.join(path,'Seglabels') total_num = len(files) name2label = c459259l('../datasets/22label.txt', '/data/detect/VOC/VOCdevkit/VOC2010/labels.txt') keys = name2label.keys() for i in tqdm.tqdm(range(total_num)): afile = files[i] file_path = os.path.join(path, afile) if os.path.isfile(file_path): if os.path.getsize(file_path) == 0: continue mat_idx = afile[:-4] mat_file = sio(file_path) mat_file = np.array(mat_file['LabelMap']).astype(np.int) h, w = mat_file.shape[:2] tmp_label = np.zeros([h, w]) for tmp in keys: tmp_label[mat_file == int(tmp)] = int(name2label[tmp]) tmp_label = tmp_label.astype(np.uint8) #here is a bug 459 -> 256 # label_img=Image.fromarray(mat_file.reshape(mat_file.shape[0],mat_file.shape[1])) dst_path = os.path.join(labels_path, mat_idx + '.png') cv2.imwrite(dst_path, tmp_label)
import os from scipy.io import loadmat as sio import numpy as np import PIL.Image as Image import matplotlib.pyplot as plt #path='/home/dl/DL_dataset/VOCdevkit/trainval' path = os.path.join(os.getcwd(), 'GroundTruth_trainval_mat') files = os.listdir(path) labels_path = os.path.join(os.getcwd(), 'GroundTruth_trainval_png') for afile in files: file_path = os.path.join(path, afile) if os.path.isfile(file_path): if os.path.getsize(file_path) == 0: continue mat_idx = afile[:afile.find('.mat')] mat_file = sio(file_path) mat_file = np.array(mat_file['LabelMap']) #print mat_file.keys() mat_file = mat_file.astype(np.uint8) label_img = Image.fromarray( mat_file.reshape(mat_file.shape[0], mat_file.shape[1])) dst_path = os.path.join(labels_path, mat_idx + '.png') print(dst_path) label_img.save(dst_path)
[192, 0, 0], [64, 128, 0], [192, 128, 0], [64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128], [0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0], [0, 64, 128]], dtype='uint8').flatten() for afile in files: file_path=os.path.join(path,afile) if os.path.isfile(file_path): if os.path.getsize(file_path)==0: continue mat_idx=afile[:afile.find('.mat')] mat_file=sio(file_path) mat_file=mat_file['data'] labels=np.argmax(mat_file,axis=2).astype(np.uint8) label_img=Image.fromarray(labels.reshape(labels.shape[0],labels.shape[1])) label_img.putpalette(palette) label_img=label_img.transpose(Image.FLIP_LEFT_RIGHT) label_img = label_img.rotate(90) dst_path=os.path.join(labels_path,mat_idx+'.png') label_img.save(dst_path)
""" Created on Mon Feb 20 17:20:58 2017 @author: aliTakin """ import numpy as np #from sklearn.svm import svc import matplotlib.pyplot as plt from scipy.io import loadmat as sio from sklearn.datasets import load_digits from sklearn.linear_model import LogisticRegression from sklearn.model_selection import cross_val_score from sklearn.feature_selection import RFECV from sklearn.metrics import accuracy_score data = sio('arcene.mat') y_train = np.ravel(data['y_train']) y_test = np.ravel(data['y_test']) X_train = data['X_train'] X_test = data['X_test'] rfecv = RFECV(estimator=LogisticRegression(), step=50, cv=10, scoring='accuracy') rfecv.fit(X_train, y_train) print(rfecv.n_features_) lr1 = LogisticRegression() lr1.fit(X_train, y_train) score_lr1 = accuracy_score(y_test, lr1.predict(X_test)) print(score_lr1)