plt.close('all')
DB_train_dir = 'Data/train'
DB_train_csv = 'Data/train.csv'
db1 = MyDatabase(DB_train_dir, DB_train_csv)
edge = Edge()
DB_test_dir = 'Data/test'
DB_test_csv = 'Data/test.csv'
db2 = MyDatabase(DB_test_dir, DB_test_csv)
# check shape
assert edge_kernels.shape == (5, 2, 2)
# evaluate database
APs, res = myevaluate(db1, db2, edge.make_samples, depth=100, d_type='d1')
cls_MAPs = []
for cls, cls_APs in APs.items():
MAP = np.mean(cls_APs)
print("Class {}, MAP {}".format(cls, MAP))
cls_MAPs.append(MAP)
print("MMAP", np.mean(cls_MAPs))
for i in range(len(db2)):
saveName = "/content/traitement_images/Data/result_edge/" + res[i] + "/" + \
db2.data.img[i].split('/')[-1]
bid = imageio.imread(db2.data.img[i])
mping.imsave(saveName, bid / 255)
db1 = Database(DB_train_dir, DB_train_csv)
print('DB length', len(db1))
color = Color()
DB_validation_dir = '../dataset/validation'
DB_validation_csv = '../result/validation.csv'
db2 = Database(DB_validation_dir, DB_validation_csv)
print('DB length', len(db2))
# evaluate database
APs, res = myevaluate(db1,
db2,
color.make_samples,
depth=depth,
d_type='d1')
#APs, APn = evaluate_class(db, f_class=Color, d_type=d_type, depth=depth)
cls_MAPs = []
for cls, cls_APs in APs.items():
MAP = np.mean(cls_APs)
print("Class {}, MAP {}".format(cls, MAP))
cls_MAPs.append(MAP)
print("MMAP", np.mean(cls_MAPs))
dir = "../result/results/"
for root, dirs, files in os.walk(dir, topdown=False):
for name in files:
os.remove(os.path.join(root, name))
samples.append({
'img': d_img,
'cls': d_cls,
'hist': d_hist
})
cPickle.dump(samples, open(os.path.join(cache_dir, sample_cache), "wb", True))
return samples
if __name__ == "__main__":
dbTrain = MyDatabase("database/train", "database/train/data_train.csv")
print("Train db length: ", len(dbTrain))
color = Color()
dbTest = MyDatabase("database/test", "database/test/data_test.csv")
print("Test db length: ", len(dbTest))
# evaluate database
APs, res = myevaluate(dbTrain, dbTest, color.make_samples, depth=depth, d_type="d1")
# add pictures in prediction folder under the predicted class folder
path = "/Users/johanncarfantan/Documents/ENSSAT/IMR3/AnalyseDimages/Partie 1/predictions/"
for i in range(len(dbTest)):
saveName = path + res[i] + "/" + dbTest.data.img[i].split('/')[-1]
bid = imageio.imread(dbTest.data.img[i])
if not os.path.exists(path + res[i]):
os.makedirs(path + res[i])
mpimg.imsave(saveName, bid / 255.)
# cls_MAPs.append(MAP)
# print("MMAP", np.mean(cls_MAPs))
plt.close('all')
DB_train_dir = '../dataset/train'
DB_train_csv = '../result/train.csv'
db1 = Database(DB_train_dir, DB_train_csv)
print('DB length', len(db1))
edge = Edge()
DB_test_dir = '../dataset/test'
DB_test_csv = '../result/test.csv'
db2 = Database(DB_test_dir, DB_test_csv)
print('DB length', len(db2))
# check shape
assert edge_kernels.shape == (5, 2, 2)
# evaluate database
APs = myevaluate(db1, db2, edge.make_samples, depth=depth, d_type='d1')
#APs, APn = evaluate_class(db, f_class=Color, d_type=d_type, depth=depth)
cls_MAPs = []
for cls, cls_APs in APs.items():
MAP = np.mean(cls_APs)
print("Class {}, MAP {}".format(cls, MAP))
cls_MAPs.append(MAP)
print("MMAP", np.mean(cls_MAPs))
cPickle.dump(
samples, open(os.path.join(cache_dir, sample_cache), "wb",
True))
return samples
if __name__ == "__main__":
plt.close('all')
DB_train_dir = 'Data/train'
DB_train_csv = 'Data/train.csv'
db1 = MyDatabase(DB_train_dir, DB_train_csv)
daisy = Daisy()
DB_test_dir = 'Data/test'
DB_test_csv = 'Data/test.csv'
db2 = MyDatabase(DB_test_dir, DB_test_csv)
# evaluate database
APs, res = myevaluate(db1, db2, daisy, depth=depth, d_type='d1')
cls_MAPs = []
for cls, cls_APs in APs.items():
MAP = np.mean(cls_APs)
print("Class {}, MAP {}".format(cls, MAP))
cls_MAPs.append(MAP)
print("MMAP", np.mean(cls_MAPs))