def resize(image, annotations_list, img_data, size):
res_image = copy.deepcopy(image)
res_image["width"] = size[1]
res_image["height"] = size[0]
res_ann = []
res_img_data = wmli.resize_img(img_data, size, keep_aspect_ratio=True)
x_scale = res_img_data.shape[1] / img_data.shape[1]
y_scale = res_img_data.shape[0] / img_data.shape[0]
for ann in annotations_list:
bbox = (np.array(ann["bbox"]) *
np.array([x_scale, y_scale, x_scale, y_scale])).astype(
np.int32)
segmentation = wmli.resize_img(ann["segmentation"],
size=size,
keep_aspect_ratio=True,
interpolation=cv2.INTER_NEAREST)
category = copy.deepcopy(ann["category_id"])
res_ann.append({
"bbox": bbox,
"segmentation": segmentation,
"category_id": category
})
return res_image, res_ann, res_img_data
def trans_data(data_dir,save_dir):
global name_to_id_dict
wmlu.show_dict(name_to_id_dict)
wmlu.create_empty_dir(save_dir,remove_if_exists=False)
def name_to_id(x):
return name_to_id_dict[x]
ignored_labels = ["construction--barrier--ambiguous","construction--barrier--separator"]
data = LabelMeData(label_text2id=name_to_id, shuffle=False)
data.read_data(data_dir)
for i,x in enumerate(data.get_items()):
full_path, img_info, category_ids, category_names, boxes, binary_mask, area, is_crowd, num_annotations_skipped = x
if len(category_ids) == 0:
print(f"Skip {full_path}")
continue
new_mask = odm.dense_mask_to_sparse_mask(binary_mask,category_ids,default_label=255)
#r_base_name = wmlu.base_name(full_path)
r_base_name = f"IMG_{i+1:05d}"
base_name = r_base_name+".png"
save_path = os.path.join(save_dir,base_name)
if resize_size is not None:
new_mask = wmli.resize_img(new_mask,resize_size,keep_aspect_ratio=True,interpolation=cv2.INTER_NEAREST)
img = wmli.imread(full_path)
img = wmli.resize_img(img,resize_size,keep_aspect_ratio=True)
img_save_path = os.path.join(save_dir,r_base_name+".jpg")
wmli.imwrite(img_save_path,img)
new_mask = new_mask.astype(np.uint8)
if os.path.exists(save_path):
print(f"WARNING: File {save_path} exists.")
cv2.imwrite(save_path,new_mask)
sys.stdout.write(f"\r{i}")
def create_tf_example(image, annotations):
global src_file_index
image_height = image['img_height']
image_width = image['img_width']
img_path = image['img_path']
if RECORD_IMG_SIZE is None:
with tf.gfile.GFile(img_path, 'rb') as fid:
encoded_jpg = fid.read()
else:
img = wmli.imread(img_path)
img = wmli.resize_img(img, RECORD_IMG_SIZE, keep_aspect_ratio=True)
encoded_jpg = wmli.encode_img(img)
xmin = []
xmax = []
ymin = []
ymax = []
is_crowd = []
category_ids = []
for l, box in annotations:
xmin.append(box[1])
xmax.append(box[3])
ymin.append(box[0])
ymax.append(box[2])
is_crowd.append(False)
category_ids.append(l)
if len(xmin) == 0:
return None
feature_dict = {
'image/height': dataset_util.int64_feature(image_height),
'image/width': dataset_util.int64_feature(image_width),
'image/filename': dataset_util.bytes_feature(img_path.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/label':
dataset_util.int64_list_feature(category_ids),
'image/object/is_crowd': dataset_util.int64_list_feature(is_crowd),
}
example = tf.train.Example(features=tf.train.Features(
feature=feature_dict))
return example
def show_anchor_box(img_file,boxes,size=None):
nr = boxes.shape[0]
classes = []
scores = []
for i in range(nr):
classes.append(0)
scores.append(1)
img = wmli.imread(img_file)
if size is not None:
img = wmli.resize_img(img,(size[1],size[0]))
odv.bboxes_draw_on_img(img, classes, scores, boxes)
plt.figure(figsize=(10,10))
plt.imshow(img)
plt.show()
return img
dataset.read_data("/home/wj/ai/mldata/boesemantic")
save_dir = wmlu.home_dir("ai/tmp/boe_images2")
wmlu.create_empty_dir(save_dir,remove_if_exists=False)
color_map = fill_colormap_and_names("/home/wj/ai/mldata/mapillary_vistas/config_v2.0.json")
def text_fn(l):
if l in ID_TO_READABLE_NAME:
return ID_TO_READABLE_NAME[l]
else:
return "NA"
def color_fn(l):
return color_map[l*3:l*3+3]
legend_img = draw_legend(list(ID_TO_NAME.keys()),text_fn,img_size=(2448,300),color_fn=color_fn)
for ifn,img,mask in dataset.get_items():
base_name = wmlu.base_name(ifn)
wmlu.safe_copy(ifn,save_dir)
rgb_mask = convert_semantic_to_rgb(mask,color_map,True)
if rgb_mask.shape[0] != legend_img.shape[0]:
legend_img = wmli.resize_img(legend_img,(legend_img.shape[1],rgb_mask.shape[0]))
rgb_mask = np.concatenate([rgb_mask,legend_img],axis=1)
mask_path = os.path.join(save_dir,base_name+".png")
wmli.imwrite(mask_path,rgb_mask)
mask_image = draw_semantic_on_image(img,mask,color_map,ignored_label=255)
mask_image = np.concatenate([mask_image,legend_img],axis=1)
mask_image_path = os.path.join(save_dir,base_name+"1.png")
wmli.imwrite(mask_image_path,mask_image)
text_to_id[t] = i + 1
id_to_text[i + 1] = t
text_to_id[" "] = 69
def name_to_id(name):
return text_to_id[name]
data = PascalVOCData(label_text2id=name_to_id, shuffle=True)
data.read_data("/home/vghost/ai/mldata2/ocrdata/rdatasv20/train")
MIN_IMG_SIZE = 768
for x in data.get_items():
full_path, category_ids, category_names, boxes, binary_mask, area, is_crowd, num_annotations_skipped = x
img = wmli.imread(full_path)
if img.shape[0] < MIN_IMG_SIZE or img.shape[1] < MIN_IMG_SIZE:
img = wmli.resize_img(img, [MIN_IMG_SIZE, MIN_IMG_SIZE],
keep_aspect_ratio=True)
def text_fn(classes, scores):
return id_to_text[classes]
odv.bboxes_draw_on_imgv2(img=img,
classes=category_ids,
scores=None,
bboxes=boxes,
color_fn=None,
text_fn=text_fn,
thickness=2,
show_text=True,
fontScale=0.8)
plt.figure()
plt.imshow(img)