def imshow_bboxes(img,
bboxes,
bbox_color=(0, 255, 0),
thickness=1,
show=True,
win_name='',
wait_time=0,
out_file=None):
"""Draw bboxes on an image.
Args:
img (str or ndarray): The image to be displayed.
bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4).
bbox_color (RGB value): Color of bbox lines.
thickness (int): Thickness of lines.
show (bool): Whether to show the image.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
out_file (str or None): The filename to write the image.
"""
assert bboxes.ndim == 2
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
img = imread(img)
for bbox in bboxes:
left_top = (bbox[0], bbox[1])
right_bottom = (bbox[2], bbox[3])
cv2.rectangle(img, left_top, right_bottom, bbox_color, thickness)
if show:
cv2.imshow(win_name, imread(img))
cv2.waitKey(wait_time)
if out_file is not None:
imwrite(img, out_file)
def imshow_det_bboxes(self,
img,
bboxes,
texts,
out_file):
# draw text
def change_cv2_draw(image, strs, local, sizes, color):
cv2img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
pilimg = Image.fromarray(cv2img)
draw = ImageDraw.Draw(pilimg)
font = ImageFont.truetype('resource/simsun.ttc', sizes, encoding="utf-8")
draw.text(local, strs, color, font=font)
image = cv2.cvtColor(np.array(pilimg), cv2.COLOR_RGB2BGR)
return image
img = imread(img)
bbox_color = (255, 0, 0)
text_color = (0, 0, 255)
for i in range(len(texts)):
bbox = bboxes[i].astype(np.int32)
text = texts[i]
cv2.drawContours(img, [bbox], -1, bbox_color, 2)
tl = np.min(bbox, 0)
img = change_cv2_draw(img, text, (tl[0], tl[1]), 20, text_color)
imwrite(img, out_file)
def show_rmask(data,
result,
img_norm_cfg,
class_names,
score_thr=0.3,
file_name='0.png'):
bbox_result, segm_result, rbbox_result = result
img_tensor = data['img'][0]
img_metas = data['img_meta'][0].data[0]
imgs = tensor2imgs(img_tensor, **img_norm_cfg)
for img, img_meta in zip(imgs, img_metas):
h, w, _ = img_meta['img_shape']
img_show = img[:h, :w, :]
bboxes = np.vstack(bbox_result)
rbboxes = np.vstack(rbbox_result)
# draw segmentation masks
if segm_result is not None:
segms = mmcv.concat_list(segm_result)
inds = np.where(bboxes[:, -1] > score_thr)[0]
for i in inds:
color_mask = np.random.randint(0, 256, (1, 3), dtype=np.uint8)
mask = maskUtils.decode(segms[i]).astype(np.bool)
img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
# draw rbbox
labels = [
np.full(bbox.shape[0], i, dtype=np.int32)
for i, bbox in enumerate(bbox_result)
]
labels = np.concatenate(labels)
img = imread(img_show)
scores = rbboxes[:, -1]
inds = scores > score_thr
bboxes = bboxes[inds, :]
rbboxes = rbboxes[inds, :8]
labels = labels[inds]
rbbox_color = (0, 0, 255)
text_color = (0, 255, 0)
font_scale = 0.5
'''
for rbbox, bbox, label in zip(rbboxes, bboxes, labels):
bbox_int = bbox.astype(np.int32)
rbbox_int = rbbox.astype(np.int32)
rbbox_int = rbbox_int.reshape(4,2)
cv2.drawContours(img,[rbbox_int],0,rbbox_color,2)
label_text = class_names[
label] if class_names is not None else 'cls {}'.format(label)
if len(bbox) > 4:
label_text += '|{:.02f}'.format(bbox[-1])
cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] - 2),
cv2.FONT_HERSHEY_COMPLEX, font_scale, text_color)
'''
cv2.imwrite(file_name, img)
def imshow_tracklets(img,
bboxes,
labels=None,
ids=None,
thickness=2,
font_scale=0.4,
show=False,
win_name='',
color=None,
out_file=None):
assert bboxes.ndim == 2
assert labels.ndim == 1
assert bboxes.shape[0] == labels.shape[0]
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
if isinstance(img, str):
img = imread(img)
i = 0
for bbox, label in zip(bboxes, labels):
x1, y1, x2, y2, _ = bbox.astype(np.int32)
if ids is not None:
if color is None:
bbox_color = random_color(ids[i])
bbox_color = [int(255 * _c) for _c in bbox_color][::-1]
else:
bbox_color = mmcv.color_val(color)
img[y1:y1 + 12, x1:x1 + 20, :] = bbox_color
cv2.putText(img,
str(ids[i]), (x1, y1 + 10),
cv2.FONT_HERSHEY_COMPLEX,
font_scale,
color=color_val('black'))
else:
if color is None:
bbox_color = color_val('green')
else:
bbox_color = mmcv.color_val(color)
cv2.rectangle(img, (x1, y1), (x2, y2), bbox_color, thickness=thickness)
if bbox[-1] < 0:
bbox[-1] = np.nan
label_text = '{:.02f}'.format(bbox[-1])
img[y1 - 12:y1, x1:x1 + 30, :] = bbox_color
cv2.putText(img,
label_text, (x1, y1 - 2),
cv2.FONT_HERSHEY_COMPLEX,
font_scale,
color=color_val('black'))
i += 1
if show:
imshow(img, win_name)
if out_file is not None:
imwrite(img, out_file)
return img
def imshow(img, win_name='', wait_time=0):
"""Show an image.
Args:
img (str or ndarray): The image to be displayed.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
"""
cv2.imshow(win_name, imread(img))
cv2.waitKey(wait_time)
def imshow_det_bboxes(img,
bboxes,
labels,
class_names=None,
score_thr=0,
bbox_color='green',
text_color='green',
thickness=1,
font_scale=0.5):
"""Draw bboxes and class labels (with scores) on an image.
Args:
img (str or ndarray): The image to be displayed.
bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4) or
(n, 5).
labels (ndarray): Labels of bboxes.
class_names (list[str]): Names of each classes.
score_thr (float): Minimum score of bboxes to be shown.
bbox_color (str or tuple or :obj:`Color`): Color of bbox lines.
text_color (str or tuple or :obj:`Color`): Color of texts.
thickness (int): Thickness of lines.
font_scale (float): Font scales of texts.
"""
assert bboxes.ndim == 2
assert labels.ndim == 1
assert bboxes.shape[0] == labels.shape[0]
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
img = imread(img)
if score_thr > 0:
assert bboxes.shape[1] == 5
scores = bboxes[:, -1]
inds = scores > score_thr
bboxes = bboxes[inds, :]
labels = labels[inds]
bbox_color = color_val(bbox_color)
text_color = color_val(text_color)
for bbox, label in zip(bboxes, labels):
bbox_int = bbox.astype(np.int32)
left_top = (bbox_int[0], bbox_int[1])
right_bottom = (bbox_int[2], bbox_int[3])
cv2.rectangle(img,
left_top,
right_bottom,
bbox_color,
thickness=thickness)
label_text = class_names[
label] if class_names is not None else 'cls {}'.format(label)
if len(bbox) > 4:
label_text += '|{:.02f}'.format(bbox[-1])
cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] - 2),
cv2.FONT_HERSHEY_COMPLEX, font_scale, text_color)
return img
def imshow_bboxes(img,
bboxes,
colors='green',
top_k=-1,
thickness=1,
show=True,
win_name='',
wait_time=0,
out_file=None):
"""Draw bboxes on an image.
Args:
img (str or ndarray): The image to be displayed.
bboxes (list or ndarray): A list of ndarray of shape (k, 4).
colors (list[str or tuple or Color]): A list of colors.
top_k (int): Plot the first k bboxes only if set positive.
thickness (int): Thickness of lines.
show (bool): Whether to show the image.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
out_file (str, optional): The filename to write the image.
Returns:
ndarray: The image with bboxes drawn on it.
"""
img = imread(img)
img = np.ascontiguousarray(img)
if isinstance(bboxes, np.ndarray):
bboxes = [bboxes]
if not isinstance(colors, list):
colors = [colors for _ in range(len(bboxes))]
colors = [color_val(c) for c in colors]
assert len(bboxes) == len(colors)
for i, _bboxes in enumerate(bboxes):
_bboxes = _bboxes.astype(np.int32)
if top_k <= 0:
_top_k = _bboxes.shape[0]
else:
_top_k = min(top_k, _bboxes.shape[0])
for j in range(_top_k):
left_top = (_bboxes[j, 0], _bboxes[j, 1])
right_bottom = (_bboxes[j, 2], _bboxes[j, 3])
cv2.rectangle(img,
left_top,
right_bottom,
colors[i],
thickness=thickness)
if show:
imshow(img, win_name, wait_time)
if out_file is not None:
imwrite(img, out_file)
return img
def imshow_bboxes_custom(img,
bboxes,
colors='green',
top_k=-1,
thickness=1,
show=True,
win_name='',
wait_time=0,
out_file=None):
"""Draw bboxes on an image.
Args:
img (str or ndarray): The image to be displayed.
bboxes (list or ndarray): A list of ndarray of shape (k, 4).
colors (list[str or tuple or Color]): A list of colors.
top_k (int): Plot the first k bboxes only if set positive.
thickness (int): Thickness of lines.
show (bool): Whether to show the image.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
out_file (str, optional): The filename to write the image.
"""
img = imread(img)
if isinstance(bboxes, np.ndarray):
bboxes = [bboxes]
if not isinstance(colors, list):
colors = [colors for _ in range(len(bboxes))]
colors = [color_val(c) for c in colors]
assert len(bboxes) == len(colors)
for i, _bboxes in enumerate(bboxes):
label_text = _bboxes[:, 4]
color_text = color_val('green')
_bboxes = _bboxes.astype(np.int32)
if top_k <= 0:
_top_k = _bboxes.shape[0]
else:
_top_k = min(top_k, _bboxes.shape[0])
for j in range(_top_k):
left_top = (_bboxes[j, 0], _bboxes[j, 1])
right_bottom = (_bboxes[j, 2], _bboxes[j, 3])
cv2.rectangle(img,
left_top,
right_bottom,
colors[i],
thickness=thickness)
cv2.putText(img, '{:.02f}'.format(label_text[j]),
(_bboxes[j, 0], _bboxes[j, 3] - 2),
cv2.FONT_HERSHEY_COMPLEX, 1, color_text)
if show:
imshow(img, win_name, wait_time)
if out_file is not None:
imwrite(img, out_file)
def imshow_polygons(img,
bboxes,
polygons,
labels,
class_names=None,
score_thr=0,
out_file=None):
assert bboxes.ndim == 2
assert labels.ndim == 1
assert bboxes.shape[0] == labels.shape[0]
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
img = imread(img)
im = img[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(12, 12))
fig = ax.imshow(im, aspect='equal')
plt.axis('off')
fig.axes.get_xaxis().set_visible(False)
fig.axes.get_yaxis().set_visible(False)
if score_thr > 0:
assert bboxes.shape[1] == 5
scores = bboxes[:, -1]
inds = scores > score_thr
bboxes = bboxes[inds, :]
polygons = polygons[inds, :]
labels = labels[inds]
for bbox, label, polygon in zip(bboxes, labels, polygons):
bbox_int = bbox.astype(np.int32)
left_top = (bbox_int[0], bbox_int[1])
right_bottom = (bbox_int[2], bbox_int[3])
poly = polygon.reshape(-1, 2).astype(np.int32)
color = np.random.rand(3)
ax.add_patch(
plt.Polygon(poly,
fill=True,
color=color,
alpha=0.5,
edgecolor=None))
ax.add_patch(
plt.Polygon(poly, fill=False, edgecolor='w', linewidth=1.0))
label_text = class_names[
label] if class_names is not None else f'cls {label}'
if len(bbox) > 4:
label_text += f'|{bbox[-1]:.02f}'
if out_file is not None:
plt.savefig(out_file)
plt.savefig(out_file.replace('jpg', 'pdf'))
plt.cla()
plt.close('all')
def imshow(img, win_name='', wait_time=0):
"""Show an image.
Args:
img (str or ndarray): The image to be displayed.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
"""
# cv2.namedWindow("result",0)
# cv2.resizeWindow("result",1920,1080)
cv2.imshow('result', imread(img))
cv2.waitKey(wait_time)
def show_rbbox_color(data,
result,
img_norm_cfg,
class_names,
score_thr=0.3,
file_name='0.png'):
rbbox_result = result
img_tensor = data['img'][0]
img_metas = data['img_meta'][0].data[0]
imgs = tensor2imgs(img_tensor, **img_norm_cfg)
for img, img_meta in zip(imgs, img_metas):
h, w, _ = img_meta['img_shape']
img_show = img[:h, :w, :]
rbboxes = np.vstack(rbbox_result)
# draw rbbox
labels = [
np.full(rbbox.shape[0], i, dtype=np.int32)
for i, rbbox in enumerate(rbbox_result)
]
labels = np.concatenate(labels)
img = imread(img_show)
scores = rbboxes[:, -1]
inds = scores > score_thr
rbboxes = rbboxes[inds, :8]
labels = labels[inds]
# rbbox_color = ncolors(16)
rbbox_color = [[247, 11, 11], [244, 103, 19], \
[250, 199, 48], [220, 245, 45], [150, 247, 52], \
[69, 244, 44], [18, 243, 75], [27, 251, 167], \
[38, 248, 248], [18, 158, 242], [15, 74, 249], \
[33, 2, 253], [147, 44, 250], [220, 29, 248], \
[243, 16, 186], [250, 43, 121]]
text_color = (0, 255, 0)
font_scale = 0.5
for rbbox, score, label in zip(rbboxes, scores, labels):
rbbox_int = rbbox.astype(np.int32)
rbbox_int = rbbox_int.reshape(4, 2)
cv2.drawContours(img, [rbbox_int], 0, rbbox_color[label], 2)
# label_text = class_names[
# label] if class_names is not None else 'cls {}'.format(label)
# label_text += '|{:.02f}'.format(score)
# cv2.putText(img, label_text, (rbbox_int[0][0], rbbox_int[0][1] - 2),
# cv2.FONT_HERSHEY_COMPLEX, font_scale, text_color)
cv2.imwrite(file_name, img)
def imshow(img, win_name='', wait_time=0):
cv2.imshow(win_name, imread(img))
if wait_time == 0: # prevent from hangning if windows was closed
while True:
ret = cv2.waitKey(1)
closed = cv2.getWindowProperty(win_name, cv2.WND_PROP_VISIBLE) < 1
# if user closed window or if some key pressed
if closed or ret != -1:
break
else:
ret = cv2.waitKey(wait_time)
def imshow(img, win_name='', wait_time=0):
"""Show an image.
Args:
img (str or ndarray): The image to be displayed.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
"""
while True:
cv2.imshow(win_name, imread(img))
k = cv2.waitKey(wait_time) & 0xff
if k == 27:
break
cv2.destroyAllWindows()
def flowread(flow_or_path, quantize=False, concat_axis=0, *args, **kwargs):
"""Read an optical flow map.
Args:
flow_or_path (ndarray or str): A flow map or filepath.
quantize (bool): whether to read quantized pair, if set to True,
remaining args will be passed to :func:`dequantize_flow`.
concat_axis (int): The axis that dx and dy are concatenated,
can be either 0 or 1. Ignored if quantize is False.
Returns:
ndarray: Optical flow represented as a (h, w, 2) numpy array
"""
if isinstance(flow_or_path, np.ndarray):
if (flow_or_path.ndim != 3) or (flow_or_path.shape[-1] != 2):
raise ValueError('Invalid flow with shape {}'.format(
flow_or_path.shape))
return flow_or_path
elif not is_str(flow_or_path):
raise TypeError(
'"flow_or_path" must be a filename or numpy array, not {}'.format(
type(flow_or_path)))
if not quantize:
with open(flow_or_path, 'rb') as f:
try:
header = f.read(4).decode('utf-8')
except Exception:
raise IOError('Invalid flow file: {}'.format(flow_or_path))
else:
if header != 'PIEH':
raise IOError(
'Invalid flow file: {}, header does not contain PIEH'.
format(flow_or_path))
w = np.fromfile(f, np.int32, 1).squeeze()
h = np.fromfile(f, np.int32, 1).squeeze()
flow = np.fromfile(f, np.float32, w * h * 2).reshape((h, w, 2))
else:
assert concat_axis in [0, 1]
cat_flow = imread(flow_or_path, flag='unchanged')
if cat_flow.ndim != 2:
raise IOError(
'{} is not a valid quantized flow file, its dimension is {}.'.
format(flow_or_path, cat_flow.ndim))
assert cat_flow.shape[concat_axis] % 2 == 0
dx, dy = np.split(cat_flow, 2, axis=concat_axis)
flow = dequantize_flow(dx, dy, *args, **kwargs)
return flow.astype(np.float32)
def imshow_det_bboxes_many(img,
bboxes,
labels,
class_names=None,
score_thr=0,
bbox_color='green',
text_color='green',
thickness=1,
font_scale=0.5,
show=True,
win_name='',
wait_time=0,
out_file=None):
"""Draw bboxes and class labels (with scores) on an image.
Args:
img (str or ndarray): The image to be displayed.
bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4) or
(n, 5).
labels (ndarray): Labels of bboxes.
class_names (list[str]): Names of each classes.
score_thr (float): Minimum score of bboxes to be shown.
bbox_color (str or tuple or :obj:`Color`): Color of bbox lines.
text_color (str or tuple or :obj:`Color`): Color of texts.
thickness (int): Thickness of lines.
font_scale (float): Font scales of texts.
show (bool): Whether to show the image.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
out_file (str or None): The filename to write the image.
Returns:
ndarray: The image with bboxes drawn on it.
"""
assert bboxes.ndim == 2
assert labels.ndim == 1
assert bboxes.shape[0] == labels.shape[0]
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
img = imread(img)
if score_thr > 0:
assert bboxes.shape[1] == 5
scores = bboxes[:, -1]
inds = scores > score_thr
bboxes = bboxes[inds, :]
labels = labels[inds]
bbox_color01 = color_val(bbox_color)
bbox_color02 = color_val('red')
bbox_color03 = color_val('blue')
def test_model_inference(cfg_file):
tmp_dir = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
config_file = os.path.join(tmp_dir, cfg_file)
model = build_model(config_file)
with pytest.raises(AssertionError):
model_inference(model, 1)
sample_img_path = os.path.join(tmp_dir, '../demo/demo_text_det.jpg')
model_inference(model, sample_img_path)
# numpy inference
img = imread(sample_img_path)
model_inference(model, img)
def test_model_batch_inference_det(cfg_file):
tmp_dir = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
config_file = os.path.join(tmp_dir, cfg_file)
model = build_model(config_file)
sample_img_path = os.path.join(tmp_dir, '../demo/demo_text_det.jpg')
results = model_inference(model, [sample_img_path], batch_mode=True)
assert len(results) == 1
# numpy inference
img = imread(sample_img_path)
results = model_inference(model, [img], batch_mode=True)
assert len(results) == 1
def show_bbox(data,
result,
img_norm_cfg,
class_names,
score_thr=0.3,
file_name='0.png'):
bbox_result = result
img_tensor = data['img'][0]
img_metas = data['img_meta'][0].data[0]
imgs = tensor2imgs(img_tensor, **img_norm_cfg)
for img, img_meta in zip(imgs, img_metas):
h, w, _ = img_meta['img_shape']
img_show = img[:h, :w, :]
bboxes = np.vstack(bbox_result)
# draw rbbox
labels = [
np.full(bbox.shape[0], i, dtype=np.int32)
for i, bbox in enumerate(bbox_result)
]
labels = np.concatenate(labels)
img = imread(img_show)
scores = bboxes[:, -1]
inds = scores > score_thr
bboxes = bboxes[inds, :]
labels = labels[inds]
bbox_color = (0, 255, 0)
text_color = (0, 255, 0)
font_scale = 0.5
for bbox, label in zip(bboxes, labels):
bbox_int = bbox.astype(np.int32)
cv2.rectangle(img, (bbox_int[0], bbox_int[1]),
(bbox_int[2], bbox_int[3]), bbox_color, 1)
label_text = class_names[
label] if class_names is not None else 'cls {}'.format(label)
if len(bbox) > 4:
label_text += '|{:.02f}'.format(bbox[-1])
cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] - 2),
cv2.FONT_HERSHEY_COMPLEX, font_scale, text_color)
cv2.imwrite(file_name, img)
def show_rbbox(data,
result,
img_norm_cfg,
class_names,
score_thr=0.3,
file_name='0.png'):
rbbox_result = result
img_tensor = data['img'][0]
img_metas = data['img_meta'][0].data[0]
imgs = tensor2imgs(img_tensor, **img_norm_cfg)
for img, img_meta in zip(imgs, img_metas):
h, w, _ = img_meta['img_shape']
img_show = img[:h, :w, :]
rbboxes = np.vstack(rbbox_result)
# draw rbbox
labels = [
np.full(rbbox.shape[0], i, dtype=np.int32)
for i, rbbox in enumerate(rbbox_result)
]
labels = np.concatenate(labels)
img = imread(img_show)
scores = rbboxes[:, -1]
inds = scores > score_thr
rbboxes = rbboxes[inds, :8]
labels = labels[inds]
rbbox_color = (0, 255, 0)
text_color = (0, 255, 0)
font_scale = 0.5
for rbbox, score, label in zip(rbboxes, scores, labels):
rbbox_int = rbbox.astype(np.int32)
rbbox_int = rbbox_int.reshape(4, 2)
cv2.drawContours(img, [rbbox_int], 0, rbbox_color, 1)
label_text = class_names[
label] if class_names is not None else 'cls {}'.format(label)
label_text += '|{:.02f}'.format(score)
cv2.putText(img, label_text,
(rbbox_int[0][0], rbbox_int[0][1] - 2),
cv2.FONT_HERSHEY_COMPLEX, font_scale, text_color)
cv2.imwrite(file_name, img)
def test_model_batch_inference_raises_exception_error_aug_test_recog(cfg_file):
tmp_dir = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
config_file = os.path.join(tmp_dir, cfg_file)
model = build_model(config_file)
with pytest.raises(
Exception,
match='aug test does not support inference with batch size'):
sample_img_path = os.path.join(tmp_dir, '../demo/demo_text_det.jpg')
model_inference(model, [sample_img_path, sample_img_path])
with pytest.raises(
Exception,
match='aug test does not support inference with batch size'):
img = imread(sample_img_path)
model_inference(model, [img, img])
def imshow(img, win_name='', wait_time=0):
"""Show an image.
Args:
img (str or ndarray): The image to be displayed.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
"""
cv2.imshow(win_name, imread(img))
if wait_time == 0: # prevent from hangning if windows was closed
while True:
ret = cv2.waitKey(1)
closed = cv2.getWindowProperty(win_name, cv2.WND_PROP_VISIBLE) < 1
# if user closed window or if some key pressed
if closed or ret != -1:
break
else:
ret = cv2.waitKey(wait_time)
def test_model_inference(cfg_file):
tmp_dir = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
config_file = os.path.join(tmp_dir, cfg_file)
device = 'cpu'
model = init_detector(config_file, checkpoint=None, device=device)
if model.cfg.data.test['type'] == 'ConcatDataset':
model.cfg.data.test.pipeline = model.cfg.data.test['datasets'][
0].pipeline
with pytest.raises(AssertionError):
model_inference(model, 1)
sample_img_path = os.path.join(tmp_dir, '../demo/demo_text_det.jpg')
model_inference(model, sample_img_path)
# numpy inference
img = imread(sample_img_path)
model_inference(model, img)
def show_one_image(result, file_path, output_dir):
found_image_bboxes = []
found_image_bbox_labels = []
file_name = file_path.split('/')[-1]
for class_label, per_class_result in enumerate(result):
# class_label: int
# per_class_result: number-of-bboxes x [x, y, x, y, prob]
for per_box_per_class_result in per_class_result:
found_image_bbox_labels.append(class_label)
found_image_bboxes.append(per_box_per_class_result)
if len(found_image_bbox_labels) == 0:
found_image_bboxes = np.zeros((0, 5))
found_image_bbox_labels = np.zeros((0, ))
else:
found_image_bboxes = np.asarray(found_image_bboxes).reshape((-1, 5))
found_image_bbox_labels = np.asarray(found_image_bbox_labels).reshape(
(-1))
img = imread(file_path)
height, width, _ = img.shape
imshow_det_bboxes(
img=file_path,
bboxes=found_image_bboxes,
# labels should be 0 based.
labels=found_image_bbox_labels,
class_names=CLASSES,
# no thr. show all.
score_thr=threshold,
bbox_color='green',
text_color='green',
# thickness (int): Thickness of both lines and fonts.
thickness=np.int((height * width / 480 / 480)**0.5),
# font_scale (float): Font scales of texts.
font_scale=np.float((height * width / 480 / 480)**0.5) / 2,
show=False,
win_name='',
wait_time=0,
# save result to a file.
out_file=output_dir + file_name)
def show_det_bboxes(img,
bboxes,
labels,
out_file,
gt_bboxes=None,
class_names=None,
score_thr=0.05,
bbox_color='yellow',
gt_color='green',
top_k=5):
assert bboxes.ndim == 2
assert labels.ndim == 1
assert bboxes.shape[0] == labels.shape[0]
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
img = imread(img)
if score_thr > 0:
assert bboxes.shape[1] == 5
scores = bboxes[:, -1]
inds = scores > score_thr
bboxes = bboxes[inds, :]
labels = labels[inds]
topinds = np.argsort(bboxes[:, 4])
topinds = topinds[:top_k] if len(topinds) >= top_k else topinds
bboxes = bboxes[topinds, :]
labels = labels[topinds]
bbox_color = color_val(bbox_color)
gt_color = color_val(gt_color)
for bbox, label in zip(bboxes, labels):
addBox(img, bbox, bbox_color, label, class_names=class_names)
if gt_bboxes is not None:
assert len(gt_bboxes) == 1
gt_bboxes = gt_bboxes[0]
for gt_box in gt_bboxes:
gt_box = gt_box.numpy()
addBox(img, gt_box, gt_color, 0, class_names=class_names)
imwrite(img, out_file)
def flowread(flow_or_path, quantize=False, concat_axis=0, *args, **kwargs):
'Read an optical flow map.\n\n Args:\n flow_or_path (ndarray or str): A flow map or filepath.\n quantize (bool): whether to read quantized pair, if set to True,\n remaining args will be passed to :func:`dequantize_flow`.\n concat_axis (int): The axis that dx and dy are concatenated,\n can be either 0 or 1. Ignored if quantize is False.\n\n Returns:\n ndarray: Optical flow represented as a (h, w, 2) numpy array\n '
if isinstance(flow_or_path, np.ndarray):
if ((flow_or_path.ndim != 3) or (flow_or_path.shape[(-1)] != 2)):
raise ValueError(''.join(
['Invalid flow with shape ', '{}'.format(flow_or_path.shape)]))
return flow_or_path
elif (not is_str(flow_or_path)):
raise TypeError(''.join([
'"flow_or_path" must be a filename or numpy array, not ',
'{}'.format(type(flow_or_path))
]))
if (not quantize):
with open(flow_or_path, 'rb') as f:
try:
header = f.read(4).decode('utf-8')
except Exception:
raise IOError(''.join(
['Invalid flow file: ', '{}'.format(flow_or_path)]))
else:
if (header != 'PIEH'):
raise IOError(''.join([
'Invalid flow file: ', '{}'.format(flow_or_path),
', header does not contain PIEH'
]))
w = np.fromfile(f, np.int32, 1).squeeze()
h = np.fromfile(f, np.int32, 1).squeeze()
flow = np.fromfile(f, np.float32, ((w * h) * 2)).reshape((h, w, 2))
else:
assert (concat_axis in [0, 1])
cat_flow = imread(flow_or_path, flag='unchanged')
if (cat_flow.ndim != 2):
raise IOError(''.join([
'{}'.format(flow_or_path),
' is not a valid quantized flow file, its dimension is ',
'{}'.format(cat_flow.ndim), '.'
]))
assert ((cat_flow.shape[concat_axis] % 2) == 0)
(dx, dy) = np.split(cat_flow, 2, axis=concat_axis)
flow = dequantize_flow(dx, dy, *args, **kwargs)
return flow.astype(np.float32)
def imshow_det_bboxes(self, img, bboxes, labels, show=True, out_file=None):
assert bboxes.ndim == 2
assert labels.ndim == 1
assert bboxes.shape[0] == labels.shape[0]
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
img = imread(img)
if self.score_thr > 0:
assert bboxes.shape[1] == 5
scores = bboxes[:, -1]
inds = scores > self.score_thr
bboxes = bboxes[inds, :]
labels = labels[inds]
img = np.ascontiguousarray(img)
for bbox, label in zip(bboxes, labels):
bbox_int = bbox.astype(np.int32)
left_top = (bbox_int[0], bbox_int[1])
right_bottom = (bbox_int[2], bbox_int[3])
cv2.rectangle(img,
left_top,
right_bottom,
self.colors[label],
thickness=self.thickness)
label_text = self.classes[
label] if self.classes is not None else f'cls {label}'
if len(bbox) > 4:
label_text += f'|{bbox[-1]:.02f}'
cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] -
(label * 2 * randint(0, 1))),
cv2.FONT_HERSHEY_COMPLEX, self.font_scale,
self.colors[label])
if show:
imshow(img, self.win_name, self.wait_time)
if out_file is not None:
imwrite(img, out_file)
return img
def restore_xyz_withIOU_single(self, idx, output_origin, car_cls_coco=2):
output = copy.deepcopy(output_origin)
print('idx', idx)
img_name = os.path.join(self.test_image_folder,
os.path.basename(output[2]['file_name']))
image = imread(img_name)
bboxes, segms, six_dof = output[0], output[1], output[2]
car_cls_score_pred = six_dof['car_cls_score_pred']
quaternion_pred = six_dof['quaternion_pred']
trans_pred_world = six_dof['trans_pred_world'].copy()
euler_angle = np.array(
[quaternion_to_euler_angle(x) for x in quaternion_pred])
car_labels = np.argmax(car_cls_score_pred, axis=1)
kaggle_car_labels = [self.unique_car_mode[x] for x in car_labels]
car_names = np.array([car_id2name[x].name for x in kaggle_car_labels])
assert len(bboxes[car_cls_coco]) == len(segms[car_cls_coco]) == len(kaggle_car_labels) \
== len(trans_pred_world) == len(euler_angle) == len(car_names)
# now we start to plot the image from kaggle
quaternion_semisphere_refined, flag = refine_yaw_and_roll(
image, bboxes[car_cls_coco], segms[car_cls_coco], car_names,
euler_angle, quaternion_pred, trans_pred_world,
self.car_model_dict, self.camera_matrix)
if flag:
output[2]['quaternion_pred'] = quaternion_semisphere_refined
euler_angle = np.array([
quaternion_to_euler_angle(x)
for x in output[2]['quaternion_pred']
])
trans_pred_world_refined = restore_x_y_from_z_withIOU(
image, bboxes[car_cls_coco], segms[car_cls_coco], car_names,
euler_angle, trans_pred_world, self.car_model_dict,
self.camera_matrix)
# print('change ',trans_pred_world,trans_pred_world_refined)
output[2]['trans_pred_world'] = trans_pred_world_refined
return output
def show_one_image(truth, file_path, output_dir):
found_image_bboxes = []
found_image_bbox_labels = []
file_name = file_path.split('/')[-1].split('.')[0]
for per_truth in truth:
if per_truth['filename'] == file_name:
found_image_bboxes = per_truth['ann']['bboxes']
found_image_bbox_labels = per_truth['ann']['labels'] - 1
if len(found_image_bbox_labels) == 0:
found_image_bboxes = np.zeros((0, 4))
found_image_bbox_labels = np.zeros((0, ))
img = imread(file_path)
height, width, _ = img.shape
imshow_det_bboxes(
img=file_path,
bboxes=found_image_bboxes,
# labels should be 0 based.
labels=found_image_bbox_labels,
class_names=dental_detection_classes(),
# no thr. show all.
score_thr=0,
bbox_color='green',
text_color='green',
# thickness (int): Thickness of both lines and fonts.
thickness=np.int((height * width / 480 / 480)**0.5),
# font_scale (float): Font scales of texts.
font_scale=np.float((height * width / 480 / 480)**0.5) / 2,
show=False,
win_name='',
wait_time=0,
# save result to a file.
out_file=output_dir + '{}_result.jpg'.format(file_name))
def test_model_batch_inference_raises_exception_error_free_resize_recog(
cfg_file):
tmp_dir = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
config_file = os.path.join(tmp_dir, cfg_file)
model = build_model(config_file)
with pytest.raises(
Exception,
match='Free resize do not support batch mode '
'since the image width is not fixed, '
'for resize keeping aspect ratio and '
'max_width is not give.'):
sample_img_path = os.path.join(tmp_dir, '../demo/demo_text_recog.jpg')
model_inference(
model, [sample_img_path, sample_img_path], batch_mode=True)
with pytest.raises(
Exception,
match='Free resize do not support batch mode '
'since the image width is not fixed, '
'for resize keeping aspect ratio and '
'max_width is not give.'):
img = imread(sample_img_path)
model_inference(model, [img, img], batch_mode=True)
def imshow_det_bboxes(img,
bboxes,
labels,
class_names=None,
score_thr=0,
bbox_color='green',
text_color='green',
thickness=1,
font_scale=0.5,
show=True,
win_name='',
wait_time=0,
out_file=None):
"""Draw bboxes and class labels (with scores) on an image.
Args:
img (str or ndarray): The image to be displayed.
bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4) or
(n, 5).
labels (ndarray): Labels of bboxes.
class_names (list[str]): Names of each classes.
score_thr (float): Minimum score of bboxes to be shown.
bbox_color (str or tuple or :obj:`Color`): Color of bbox lines.
text_color (str or tuple or :obj:`Color`): Color of texts.
thickness (int): Thickness of lines.
font_scale (float): Font scales of texts.
show (bool): Whether to show the image.
win_name (str): The window name.
wait_time (int): Value of waitKey param.
out_file (str or None): The filename to write the image.
Returns:
ndarray: The image with bboxes drawn on it.
"""
assert bboxes.ndim == 2
assert labels.ndim == 1
assert bboxes.shape[0] == labels.shape[0]
assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
img = imread(img)
if score_thr > 0:
assert bboxes.shape[1] == 5
scores = bboxes[:, -1]
inds = scores > score_thr
bboxes = bboxes[inds, :]
labels = labels[inds]
bbox_color01 = color_val(bbox_color)
bbox_color02 = color_val('red')
bbox_color03 = color_val('blue')
text_color = color_val(text_color)
img = np.ascontiguousarray(img)
for bbox, label in zip(bboxes, labels):
bbox_int = bbox.astype(np.int32)
left_top = (bbox_int[0], bbox_int[1])
right_bottom = (bbox_int[2], bbox_int[3])
if label == 1:
cv2.rectangle(img, left_top, right_bottom, bbox_color01, thickness=thickness)
elif label == 2:
cv2.rectangle(img, left_top, right_bottom, bbox_color02, thickness=thickness)
else:
cv2.rectangle(img, left_top, right_bottom, bbox_color03, thickness=thickness)
label_text = class_names[
label] if class_names is not None else f'cls {label}'
if len(bbox) > 4:
label_text += f'|{bbox[-1]:.02f}'
if label == 1:
cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] - 2),
cv2.FONT_HERSHEY_COMPLEX, font_scale, bbox_color02)
elif label == 2:
cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] - 2),
cv2.FONT_HERSHEY_COMPLEX, font_scale, bbox_color03)
else:
cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] - 2),
cv2.FONT_HERSHEY_COMPLEX, font_scale, bbox_color01)
if show:
imshow(img, win_name, wait_time)
if out_file is not None:
imwrite(img, out_file)
return img