100 lines
4.0 KiB
Python
100 lines
4.0 KiB
Python
# Copyright 2020 The MediaPipe Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
"""Tests for mediapipe.python.solutions.hands."""
|
|
|
|
import os
|
|
|
|
from absl.testing import absltest
|
|
from absl.testing import parameterized
|
|
import cv2
|
|
import numpy as np
|
|
import numpy.testing as npt
|
|
|
|
# resources dependency
|
|
from mediapipe.python.solutions import hands as mp_hands
|
|
|
|
TEST_IMAGE_PATH = 'mediapipe/python/solutions/testdata'
|
|
DIFF_THRESHOLOD = 20
|
|
EXPECTED_HAND_COORDINATES_PREDICTION = [[[332, 144], [323, 211], [286, 257],
|
|
[237, 289], [203, 322], [216, 219],
|
|
[138, 238], [90, 249], [51, 253],
|
|
[204, 177], [115, 184], [60, 187],
|
|
[19, 185], [208, 138], [127, 131],
|
|
[77, 124], [36, 117], [222, 106],
|
|
[159, 92], [124, 79], [93, 68]],
|
|
[[43, 570], [56, 504], [94, 459],
|
|
[146, 429], [182, 397], [167, 496],
|
|
[245, 479], [292, 469], [330, 464],
|
|
[177, 540], [265, 534], [319, 533],
|
|
[360, 536], [172, 581], [252, 587],
|
|
[304, 593], [346, 599], [157, 615],
|
|
[219, 628], [255, 638], [288, 648]]]
|
|
|
|
|
|
class HandsTest(parameterized.TestCase):
|
|
|
|
def test_invalid_image_shape(self):
|
|
hands = mp_hands.Hands()
|
|
with self.assertRaisesRegex(
|
|
ValueError, 'Input image must contain three channel rgb data.'):
|
|
hands.process(np.arange(36, dtype=np.uint8).reshape(3, 3, 4))
|
|
|
|
def test_blank_image(self):
|
|
hands = mp_hands.Hands()
|
|
image = np.zeros([100, 100, 3], dtype=np.uint8)
|
|
image.fill(255)
|
|
results = hands.process(image)
|
|
self.assertIsNone(results.multi_hand_landmarks)
|
|
self.assertIsNone(results.multi_handedness)
|
|
hands.close()
|
|
|
|
@parameterized.named_parameters(('static_image_mode', True, 1),
|
|
('video_mode', False, 5))
|
|
def test_multi_hands(self, static_image_mode, num_frames):
|
|
image_path = os.path.join(os.path.dirname(__file__), 'testdata/hands.jpg')
|
|
hands = mp_hands.Hands(
|
|
static_image_mode=static_image_mode,
|
|
max_num_hands=2,
|
|
min_detection_confidence=0.5)
|
|
image = cv2.flip(cv2.imread(image_path), 1)
|
|
|
|
def process_one_frame():
|
|
results = hands.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
|
|
handedness = [
|
|
handedness.classification[0].label
|
|
for handedness in results.multi_handedness
|
|
]
|
|
self.assertLen(handedness, 2)
|
|
multi_hand_coordinates = []
|
|
for landmarks in results.multi_hand_landmarks:
|
|
self.assertLen(landmarks.landmark, 21)
|
|
x = [landmark.x for landmark in landmarks.landmark]
|
|
y = [landmark.y for landmark in landmarks.landmark]
|
|
hand_coordinates = np.transpose(np.stack((y, x))) * image.shape[0:2]
|
|
multi_hand_coordinates.append(hand_coordinates)
|
|
self.assertLen(multi_hand_coordinates, 2)
|
|
prediction_error = np.abs(
|
|
np.asarray(multi_hand_coordinates) -
|
|
np.asarray(EXPECTED_HAND_COORDINATES_PREDICTION))
|
|
npt.assert_array_less(prediction_error, DIFF_THRESHOLOD)
|
|
|
|
for _ in range(num_frames):
|
|
process_one_frame()
|
|
hands.close()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
absltest.main()
|