"""
Calculate F1 score for ratio of positive pixels in superpixels
"""
save_path = os.path.join(rd.root_dir, 'plots_results', 'sp_thr_f1s.npz')
ratios = [0.25, 0.5, 0.75, 1.0]
res = dict()
# Self-learning
for key in rd.types:
res[key] = dict()
for seq in rd.res_dirs_dict_ksp[key][0]:
f1s = list()
cfg_ = cfg.load_and_convert(os.path.join(rd.root_dir,
seq,
'cfg.yml'))
dset = learning_dataset.LearningDataset(cfg_)
gt = dset.gt
sp_gt = dset.make_y_map_true(gt)
for r in ratios:
f1 = f1_score(gt.ravel(), (sp_gt >= r).ravel())
f1s.append(f1)
res[key][cfg_.ds_dir] = f1s
data = {'res': res, 'ratios': ratios}
np.savez(save_path, **data)
splits = utls.splitall(path_)
return os.path.join(root_dir, *splits[prefix_remove:])
for key in rd.types:
#for key in ['Brain', 'Cochlea', 'Slitlamp']:
for dir_ in rd.res_dirs_dict_wtp[key]:
print('Scoring:')
print(dir_)
# Get h5 file
path_ = os.path.join(rd.root_dir,
dir_)
# Get config
conf = cfg.load_and_convert(os.path.join(path_, 'cfg.yml'))
conf.precomp_desc_path = adjust_path(rd.root_dir,
conf.precomp_desc_path)
conf.frameFileNames = [adjust_path(rd.root_dir, f) for f in conf.frameFileNames]
conf.root_path = rd.root_dir
conf.dataOutDir = adjust_path(rd.root_dir, conf.dataOutDir)
l_dataset = learning_dataset.LearningDataset(conf, pos_thr=0.5)
gt = l_dataset.gt
file_ = os.path.join(path_,
'nn_objectness_g1',
'predictions.h5')
f = h5py.File(file_, 'r')
a_group_key = list(f.keys())[0]
#dict_ = pickle.load(open('g_for_dict', 'rb'))
#dict_['forward_tracklets']
#dict_['forward_sets']
#paths = utls.tracklet_set_to_sp_path(dict_['forward_tracklets'],
# dict_['forward_sets'],
# iter_=0)
root_dir = os.path.join('/home/laurent.lejeune/medical-labeling/',
'Dataset00/results')
#exp_dir = '2018-05-31_09-55-01_exp'
#exp_dir = '2018-05-31_09-55-40_exp'
exp_dir = '2018-05-31_09-56-40_exp'
conf = cfg.load_and_convert(os.path.join(root_dir, exp_dir, 'cfg.yml'))
pksp.main(conf)
#dataset = learning_dataset.LearningDataset(conf)
#labels = dataset.get_labels()
#im = [utls.imread(f) for f in conf.frameFileNames]
#res = np.load(os.path.join(dir_, 'results.npz'))
#list_paths_back = res['list_paths_back']
#list_paths_for = res['list_paths_for']
#seeds = utls.list_paths_to_seeds(list_paths_for,
# list_paths_back)
#seeds += list(set([p.tolist() for p in list_paths_back[-1]]))
#seeds += list(set([p.tolist() for p in list_paths_for[-1]]))
from matplotlib.backends.backend_agg import FigureCanvasAgg
from scipy.ndimage.measurements import center_of_mass
import copy
"""
Makes plots self
"""
def gray2rgb(im):
return (color.gray2rgb(im)*255).astype(np.uint8)
file_out = os.path.join(rd.root_dir, 'plots_results')
dir_ = 'Dataset30/results/2018-06-01_14-22-56_for_paths'
conf = cfg.load_and_convert(os.path.join(rd.root_dir, dir_, 'cfg.yml'))
res = np.load(os.path.join(rd.root_dir, dir_, 'results.npz'))
list_paths_back = res['list_paths_back']
list_paths_forw = res['list_paths_for']
color_sps = (0, 0, 255)
ims = []
ksp = []
# Load config
dataset = learning_dataset.LearningDataset(conf)
gt = dataset.gt
# Image
if (not os.path.exists(file_out)):
print('{} doesnt exist. Creating.'.format(file_out))
os.mkdir(file_out)
cmap = plt.get_cmap('viridis')
for key in ['Slitlamp']:
#for key in rd.types: # Types
# Get first gaze-set of every dataset
for i in [0]:
#for i in range(4):
#My model
dir_ksp = os.path.join(rd.root_dir, rd.res_dirs_dict_ksp[key][i][0])
conf = cfg.load_and_convert(os.path.join(dir_ksp, 'cfg.yml'))
print('Type: {}. Dset: {}'.format(key, conf.ds_dir))
# Load config
dataset = learning_dataset.LearningDataset(conf)
gt = dataset.gt
exp_dir = '{}_{}'.format(key, i + 1)
dir_out = os.path.join(file_out, exp_dir)
if (not os.path.exists(dir_out)):
print('{} doesnt exist. Creating.'.format(dir_out))
os.mkdir(dir_out)
file_ksp = os.path.join(dir_ksp, 'results.npz')