def test_api_post():
path = "C:\\Users\\CAU\\Desktop\\capstone\\text_recognition\demo_image"
if os.path.exists(path):
for file in os.scandir(path):
os.remove(file.path)
imagefile = request.files['image']
filename = werkzeug.utils.secure_filename(imagefile.filename)
print("\nReceived image File name : " + imagefile.filename)
imagefile.save("./text_detection/test/" + filename)
# time.sleep(5)
detection.run_detection()
# time.sleep(5)
img_files, img_bbox = load_files()
crop_img(img_files, img_bbox)
pred_str = recognition.run_recognition()
# underline detection
cfg = PredictionConfig()
# define the model
model = MaskRCNN(mode='inference', model_dir='./', config=cfg)
# load model weights
model_path = 'mask_rcnn_underline_cfg_0020.h5'
model.load_weights(model_path, by_name=True)
temp = cv2.imread("./text_detection/test/androidFlask.jpg")
yhat = model.detect([temp], verbose=0)[0]
print(len(yhat['rois']))
# [l, t], [r, t], [r, b], [l, b]
for i, file in enumerate(img_files):
txt = pd.read_csv(img_bbox[i], header=None)
df = pd.DataFrame(columns=["x1", "y1", "x2", "y2", "x3", "y3", "x4", "y4", "result_text"])
# compare
for i, bb in enumerate(txt.values):
x1, y1, x2, y2, x3, y3, x4, y4 = bb
# textbb = [x1, y1, x3, y3]
for underline in yhat['rois']:
uy1, ux1, uy2, ux2 = underline
if (ux1 + ux2) / 2 > x1 and (ux1 + ux2) / 2 < x3 and y1 < uy1 and uy1 < y3:
df = df.append({"x1": x1, "y1": y1, "x2": x2, "y2": y2, "x3": x3, "y3": y3, "x4": x4, "y4": y4,
"result_text": pred_str[i]}, ignore_index=True)
temp = cv2.rectangle(temp, (x1, y1), (x3, y3), (0, 0, 255), 3)
# top-left corner and bottom-right corner of rectangle.
df.to_csv("./result.csv")
cv2.imwrite("./result.jpg", temp)
from keras import backend as K
K.clear_session()
cuda.select_device(0)
cuda.close()
del model
return "done"
def run_main():
detection.run_detection()
img_files, img_bbox = load_files()
crop_img(img_files, img_bbox)
pred_str = recognition.run_recognition()
print("recog done")
from Mask_RCNN.mrcnn.model import MaskRCNN
cfg = PredictionConfig()
# define the model
model = MaskRCNN(mode='inference', model_dir='./', config=cfg)
# load model weights
model_path = 'mask_rcnn_underline_cfg_0019.h5'
model.load_weights(model_path, by_name=True)
temp = cv2.imread("./text_detection/test/androidFlask.jpg")
yhat = model.detect([temp], verbose=0)[0]
# [l, t], [r, t], [r, b], [l, b]
for i, file in enumerate(img_files):
txt = pd.read_csv(img_bbox[i], header=None)
df = pd.DataFrame(columns=[
"x1", "y1", "x2", "y2", "x3", "y3", "x4", "y4", "result_text"
])
# compare
#temp = []
for i, bb in enumerate(txt.values):
x1, y1, _, _, x3, y3, _, _ = bb
# textbb = [x1, y1, x3, y3]
for underline in yhat['rois']:
uy1, ux1, uy2, ux2 = underline
if (ux1 + ux2) / 2 > x1 and (
ux1 + ux2) / 2 < x3 and y1 < uy1 and uy1 < y3:
print(pred_str[i])
for num, _col in enumerate(list(df)[:-1]):
df[_col] = txt[num]
df["result_text"] = pred_str
df.to_csv("./result.csv")
def main(ann_file_path,images_path,epochs,ped_percentage,val_images_path , val_ann_file, preproType):
# train set
train_set = OurTrainDataset()
train_set.load_dataset(images_path, ann_file_path,ped_percentage, preproType) # ,ped_percentage
train_set.prepare()
print('Train images: %d' % len(train_set.image_ids))
# val set
val_set = OurALLTestDataset()
val_set.load_dataset(val_images_path, val_ann_file,preproType)
val_set.prepare()
print('Validation images: %d' % len(val_set.image_ids))
# prepare config
config = TrainConfig()
# define the model
model = MaskRCNN(mode='training', model_dir='/home/test/data/trained_models/', config=config)
# load weights (mscoco)
model.load_weights('/home/test/data/mask_rcnn_coco.h5', by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox", "mrcnn_mask"])
print('START TRAINING')
# train weights (output layers or 'heads')
model.train(train_set, val_set, learning_rate=config.LEARNING_RATE, epochs=epochs, layers='all')
print('Training DONE')
def main():
args = _get_args()
image_path = args.image_path
class_names = {1: 'mask', 2: 'no_mask', 3: 'mask_worn_incorrectly'}
inf_config = InferenceConfig()
model = MaskRCNN(mode='inference', config=inf_config, model_dir='./')
model_path = model.find_last()
model.load_weights(model_path, by_name=True)
for filename in os.listdir(image_path):
if filename.split('.')[-1] not in ['jpg', 'png', 'jpeg']:
continue
img = skimage.io.imread(image_path + filename)
img_arr = np.array(img)
img_arr = img_arr[:, :, :3]
results = model.detect([img_arr], verbose=1)
r = results[0]
display_instances(img,
r['rois'],
r['masks'],
r['class_ids'],
class_names,
r['scores'],
figsize=(10, 10))
def find(self, imgpath, outputname):
model = MaskRCNN(mode="inference",
config=self.config,
model_dir=self.config.MODEL_PATH)
print("weights_path: ", self.weights_path)
model.load_weights(self.weights_path, by_name=True)
image = skimage.io.imread(imgpath)
masks = model.detect([image], verbose=1)[0]
gray = skimage.color.gray2rgb(skimage.color.rgb2gray(image)) * 255
mask_filter = (np.sum(masks["masks"], -1, keepdims=True) >= 1)
if mask_filter.shape[0] > 0:
waldo = np.where(mask_filter, image, gray).astype(np.uint8)
img = Image.fromarray(waldo, 'RGB')
outpath = os.path.join(os.getcwd(),
os.path.basename(self.weights_path)[:-3])
if not os.path.exists(outpath):
os.makedirs(outpath)
img.save(os.path.join(outpath, outputname + ".jpg"))
else:
print("Can't find Waldo. Hmm..")
# define the prediction configuration
class PredictionConfig(Config):
# define the name of the configuration
NAME = "underline_cfg"
NUM_CLASSES = 1 + 1
# simplify GPU config
GPU_COUNT = 1
IMAGES_PER_GPU = 1
# create config
cfg = PredictionConfig()
# define the model
model = MaskRCNN(mode='inference', model_dir='./', config=cfg)
# load model weights
model_path = 'mask_rcnn_underline_cfg_0019.h5'
model.load_weights(model_path, by_name=True)
temp = cv2.imread("./text_detection/test/androidFlask.jpg")
yhat = model.detect([temp], verbose=0)[0]
print(yhat['rois'])
# plot first few images
pyplot.imshow(temp)
# plot all masks
# for j in range(len(yhat['rois'])):
# pyplot.imshow(list(yhat['rois'][j]), cmap='gray', alpha=0.3)
ax = pyplot.gca()
# plot each box
class CommaConfig(coco.CocoConfig):
NAME = 'comma.ai'
GPU_COUNT = 1
IMAGES_PER_GPU = batch_size
IMAGE_MIN_DIM = 256
IMAGE_MAX_DIM = 512
MEAN_PIXEL = mean
if __name__ == '__main__':
config = CommaConfig()
model = MaskRCNN(mode="inference", model_dir="logs", config=config)
model.load_weights('models/mask_rcnn_coco.h5', by_name=True)
for image_paths in [train_paths, test_paths]:
output_dir = os.path.join(*image_paths[0].split('/')[:2], 'seg')
os.makedirs(output_dir, exist_ok=True)
for i in tqdm(range(0, len(image_paths), batch_size)):
batch = []
for j in range(batch_size):
if i + j >= len(image_paths):
batch.append(batch[-1])
else:
image = cv2.cvtColor(cv2.imread(image_paths[i + j]),
cv2.COLOR_BGR2RGB)
GPU_COUNT = 1
NUM_CLASSES = 81
config = Config()
config.display()
ROOT_DIR = os.getcwd()
MODEL_DIR = os.path.join(ROOT_DIR, "logs")
COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")
print(COCO_MODEL_PATH)
if not os.path.exists(COCO_MODEL_PATH):
Mask_RCNN.mrcnn.utils.download_trained_weights(COCO_MODEL_PATH)
model = MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=Config())
model.load_weights(COCO_MODEL_PATH, by_name=True)
def get_cars(boxes, class_ids):
cars = []
for i, box in enumerate(boxes):
if class_ids[i] in [3, 8, 6]:
cars.append(box)
return np.array(cars)
def compute_overlaps(parked_car_boxes, car_boxes):
new_car_boxes = []
for box in car_boxes:
y1 = box[0]