class RecOp(Op):
def init_op(self):
self.ocr_reader = OCRReader(
char_dict_path="../../ppocr/utils/ppocr_keys_v1.txt")
def preprocess(self, input_dicts, data_id, log_id):
(_, input_dict), = input_dicts.items()
raw_im = base64.b64decode(input_dict["image"].encode('utf8'))
data = np.fromstring(raw_im, np.uint8)
im = cv2.imdecode(data, cv2.IMREAD_COLOR)
feed_list = []
max_wh_ratio = 0
## Many mini-batchs, the type of feed_data is list.
max_batch_size = 6 # len(dt_boxes)
# If max_batch_size is 0, skipping predict stage
if max_batch_size == 0:
return {}, True, None, ""
boxes_size = max_batch_size
rem = boxes_size % max_batch_size
h, w = im.shape[0:2]
wh_ratio = w * 1.0 / h
max_wh_ratio = max(max_wh_ratio, wh_ratio)
_, w, h = self.ocr_reader.resize_norm_img(im, max_wh_ratio).shape
norm_img = self.ocr_reader.resize_norm_img(im, max_batch_size)
norm_img = norm_img[np.newaxis, :]
feed = {"x": norm_img.copy()}
feed_list.append(feed)
return feed_list, False, None, ""
def postprocess(self, input_dicts, fetch_data, data_id, log_id):
res_list = []
if isinstance(fetch_data, dict):
if len(fetch_data) > 0:
rec_batch_res = self.ocr_reader.postprocess(
fetch_data, with_score=True)
for res in rec_batch_res:
res_list.append(res[0])
elif isinstance(fetch_data, list):
for one_batch in fetch_data:
one_batch_res = self.ocr_reader.postprocess(
one_batch, with_score=True)
for res in one_batch_res:
res_list.append(res[0])
res = {"res": str(res_list)}
return res, None, ""
class RecOp(Op):
def init_op(self):
self.ocr_reader = OCRReader(
char_dict_path="../../ppocr/utils/ppocr_keys_v1.txt")
self.get_rotate_crop_image = GetRotateCropImage()
self.sorted_boxes = SortedBoxes()
def preprocess(self, input_dicts, data_id, log_id):
(_, input_dict), = input_dicts.items()
im = input_dict["image"]
dt_boxes = input_dict["dt_boxes"]
dt_boxes = self.sorted_boxes(dt_boxes)
feed_list = []
img_list = []
max_wh_ratio = 0
for i, dtbox in enumerate(dt_boxes):
boximg = self.get_rotate_crop_image(im, dt_boxes[i])
img_list.append(boximg)
h, w = boximg.shape[0:2]
wh_ratio = w * 1.0 / h
max_wh_ratio = max(max_wh_ratio, wh_ratio)
_, w, h = self.ocr_reader.resize_norm_img(img_list[0],
max_wh_ratio).shape
imgs = np.zeros((len(img_list), 3, w, h)).astype('float32')
for id, img in enumerate(img_list):
norm_img = self.ocr_reader.resize_norm_img(img, max_wh_ratio)
imgs[id] = norm_img
print("rec image shape", imgs.shape)
feed = {"x": imgs.copy()}
return feed, False, None, ""
def postprocess(self, input_dicts, fetch_dict, log_id):
rec_res = self.ocr_reader.postprocess(fetch_dict, with_score=True)
res_lst = []
for res in rec_res:
res_lst.append(res[0])
res = {"res": str(res_lst)}
return res, None, ""
client = Client()
# TODO:load_client need to load more than one client model.
# this need to figure out some details.
client.load_client_config(sys.argv[1:])
client.connect(["127.0.0.1:9293"])
import paddle
test_img_dir = "test_img/"
ocr_reader = OCRReader(char_dict_path="../../ppocr/utils/ppocr_keys_v1.txt")
def cv2_to_base64(image):
return base64.b64encode(image).decode(
'utf8') #data.tostring()).decode('utf8')
for img_file in os.listdir(test_img_dir):
with open(os.path.join(test_img_dir, img_file), 'rb') as file:
image_data = file.read()
image = cv2_to_base64(image_data)
res_list = []
fetch_map = client.predict(feed={"x": image},
fetch=["save_infer_model/scale_0.tmp_1"],
batch=True)
one_batch_res = ocr_reader.postprocess(fetch_map, with_score=True)
for res in one_batch_res:
res_list.append(res[0])
res = {"res": str(res_list)}
print(res)
class RecOp(Op):
def init_op(self):
self.ocr_reader = OCRReader(
char_dict_path="../../ppocr/utils/ppocr_keys_v1.txt")
self.get_rotate_crop_image = GetRotateCropImage()
self.sorted_boxes = SortedBoxes()
def preprocess(self, input_dicts, data_id, log_id):
(_, input_dict), = input_dicts.items()
raw_im = input_dict["image"]
data = np.frombuffer(raw_im, np.uint8)
im = cv2.imdecode(data, cv2.IMREAD_COLOR)
dt_boxes = input_dict["dt_boxes"]
dt_boxes = self.sorted_boxes(dt_boxes)
feed_list = []
img_list = []
max_wh_ratio = 0
## Many mini-batchs, the type of feed_data is list.
max_batch_size = 6 # len(dt_boxes)
# If max_batch_size is 0, skipping predict stage
if max_batch_size == 0:
return {}, True, None, ""
boxes_size = len(dt_boxes)
batch_size = boxes_size // max_batch_size
rem = boxes_size % max_batch_size
for bt_idx in range(0, batch_size + 1):
imgs = None
boxes_num_in_one_batch = 0
if bt_idx == batch_size:
if rem == 0:
continue
else:
boxes_num_in_one_batch = rem
elif bt_idx < batch_size:
boxes_num_in_one_batch = max_batch_size
else:
_LOGGER.error(
"batch_size error, bt_idx={}, batch_size={}".format(
bt_idx, batch_size))
break
start = bt_idx * max_batch_size
end = start + boxes_num_in_one_batch
img_list = []
for box_idx in range(start, end):
boximg = self.get_rotate_crop_image(im, dt_boxes[box_idx])
img_list.append(boximg)
h, w = boximg.shape[0:2]
wh_ratio = w * 1.0 / h
max_wh_ratio = max(max_wh_ratio, wh_ratio)
_, w, h = self.ocr_reader.resize_norm_img(img_list[0],
max_wh_ratio).shape
imgs = np.zeros(
(boxes_num_in_one_batch, 3, w, h)).astype('float32')
for id, img in enumerate(img_list):
norm_img = self.ocr_reader.resize_norm_img(img, max_wh_ratio)
imgs[id] = norm_img
feed = {"x": imgs.copy()}
feed_list.append(feed)
return feed_list, False, None, ""
def postprocess(self, input_dicts, fetch_data, data_id, log_id):
res_list = []
if isinstance(fetch_data, dict):
if len(fetch_data) > 0:
rec_batch_res = self.ocr_reader.postprocess(fetch_data,
with_score=True)
for res in rec_batch_res:
res_list.append(res[0])
elif isinstance(fetch_data, list):
for one_batch in fetch_data:
one_batch_res = self.ocr_reader.postprocess(one_batch,
with_score=True)
for res in one_batch_res:
res_list.append(res[0])
res = {"res": str(res_list)}
return res, None, ""
class OCRService(WebService):
def init_det_debugger(self, det_model_config):
self.det_preprocess = Sequential([
ResizeByFactor(32, 960), Div(255),
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]), Transpose(
(2, 0, 1))
])
self.det_client = LocalPredictor()
if sys.argv[1] == 'gpu':
self.det_client.load_model_config(
det_model_config, use_gpu=True, gpu_id=0)
elif sys.argv[1] == 'cpu':
self.det_client.load_model_config(det_model_config)
self.ocr_reader = OCRReader(
char_dict_path="../../../ppocr/utils/ppocr_keys_v1.txt")
def preprocess(self, feed=[], fetch=[]):
data = base64.b64decode(feed[0]["image"].encode('utf8'))
data = np.fromstring(data, np.uint8)
im = cv2.imdecode(data, cv2.IMREAD_COLOR)
ori_h, ori_w, _ = im.shape
det_img = self.det_preprocess(im)
_, new_h, new_w = det_img.shape
det_img = det_img[np.newaxis, :]
det_img = det_img.copy()
det_out = self.det_client.predict(
feed={"x": det_img}, fetch=["save_infer_model/scale_0.tmp_1"], batch=True)
filter_func = FilterBoxes(10, 10)
post_func = DBPostProcess({
"thresh": 0.3,
"box_thresh": 0.5,
"max_candidates": 1000,
"unclip_ratio": 1.5,
"min_size": 3
})
sorted_boxes = SortedBoxes()
ratio_list = [float(new_h) / ori_h, float(new_w) / ori_w]
dt_boxes_list = post_func(det_out["save_infer_model/scale_0.tmp_1"], [ratio_list])
dt_boxes = filter_func(dt_boxes_list[0], [ori_h, ori_w])
dt_boxes = sorted_boxes(dt_boxes)
get_rotate_crop_image = GetRotateCropImage()
img_list = []
max_wh_ratio = 0
for i, dtbox in enumerate(dt_boxes):
boximg = get_rotate_crop_image(im, dt_boxes[i])
img_list.append(boximg)
h, w = boximg.shape[0:2]
wh_ratio = w * 1.0 / h
max_wh_ratio = max(max_wh_ratio, wh_ratio)
if len(img_list) == 0:
return [], []
_, w, h = self.ocr_reader.resize_norm_img(img_list[0],
max_wh_ratio).shape
imgs = np.zeros((len(img_list), 3, w, h)).astype('float32')
for id, img in enumerate(img_list):
norm_img = self.ocr_reader.resize_norm_img(img, max_wh_ratio)
imgs[id] = norm_img
feed = {"x": imgs.copy()}
fetch = ["save_infer_model/scale_0.tmp_1"]
return feed, fetch, True
def postprocess(self, feed={}, fetch=[], fetch_map=None):
rec_res = self.ocr_reader.postprocess(fetch_map, with_score=True)
res_lst = []
for res in rec_res:
res_lst.append(res[0])
res = {"res": res_lst}
return res