# image visualization
b_visualize = True
# graph visualization
b_plot = True
save = True
# weights
pesi = '../weights_13_cpm_no_vgg_out_8BIT/weights.041-0.00920.hdf5'
# model
model = net(input_shape=(1, rows, cols), weights_path=pesi)
# loading test names
test_data_names = load_names(val_seq=2, augm=0, dataset=2)
show = True
thresold = 0.3
TP = TN = FP = FN = FP_DIST = 0
FPS = []
TOTiou = []
for image in range(len(test_data_names)):
sys.stdout.write("\r%.2f%%" %
(((image + 1) / float(len(test_data_names))) * 100))
sys.stdout.flush()
seq = test_data_names[image]['image'].split('\\')[-3]
frame = 0
if checkBadFrame(seq, frame):
print 'skipped', seq, frame
continue
#limit_test = 10
limit_test = -1
b_debug = False
fulldepth = False
removeBackground = False
equalize = False
WEIGHT = 'weights'
model = EyesStatusNet(input_shape=(1, rows, cols))
model.summary()
# loading training name
train_data_names = load_names()
random.shuffle(train_data_names)
val_data_names = load_names_val()
# Data augmentation
if data_augmentation:
for i in range(1, 9):
tmp = load_names(augm=i)
train_data_names = train_data_names + tmp
# cut train
random.shuffle(train_data_names)
if limit_train == -1:
limit_train = len(train_data_names)
train_data_names = train_data_names[:limit_train]
random.shuffle(val_data_names)
# image visualization
b_visualize = True
# graph visualization
b_plot = True
save = True
# weights
pesi = '..\weights\weights.018-0.13829.hdf5'
# model
model = EyesStatusNet(input_shape=(1, rows, cols), weights_path=pesi)
# loading test sequence
test_data_names = load_names(val_seq=-1)
show = True
contAccuracy = 0
for image in range(len(test_data_names)):
seq = test_data_names[image]['image'].split('\\')[-3]
t = time.time()
test_data_X, _ = load_images(test_data_names[image:image + 1],
crop=b_crop,
rescale=b_rescale,
scale=b_scale,
b_debug=False,
normcv2=b_normcv2,
rows=rows,
fulldepth=False,
cols=cols,
limit_test = 10
#limit_test = -1
b_debug = False
fulldepth = False
removeBackground = False
equalize = False
WEIGHT = 'weights'
model = net(input_shape=(1, rows, cols))
model.summary()
# load train name
train_data_names = load_names(dataset=0)
train_data_names = train_data_names + load_names(dataset=1)
# train_data_names = load_names(dataset=2)
random.shuffle(train_data_names)
# load validation name
val_data_names = load_names_val()
# data augmentation
if data_augmentation:
for i in range(1, 9):
tmp = load_names(augm=i)
train_data_names = train_data_names + tmp
# train data cut
random.shuffle(train_data_names)
if limit_train == -1:
limit_train = len(train_data_names)