50 lines
1.6 KiB
Python
50 lines
1.6 KiB
Python
import tempfile
|
|
from collections import defaultdict
|
|
|
|
import cv2
|
|
import numpy as np
|
|
|
|
from paddle_detection import PADDLE_DET
|
|
from paddle_detection.deploy.third_engine.onnx.infer import PredictConfig
|
|
from paddle_detection.deploy.third_engine.onnx.preprocess import Compose
|
|
from util import image_util, common_util
|
|
|
|
|
|
def predict_image(infer_config, predictor, img_path):
|
|
# load preprocess transforms
|
|
transforms = Compose(infer_config.preprocess_infos)
|
|
# predict image
|
|
inputs = transforms(img_path)
|
|
inputs["image"] = np.array(inputs["image"]).astype('float32')
|
|
inputs_name = [var.name for var in predictor.get_inputs()]
|
|
inputs = {k: inputs[k][None,] for k in inputs_name}
|
|
|
|
outputs = predictor.run(output_names=None, input_feed=inputs)
|
|
|
|
bboxes = np.array(outputs[0])
|
|
result = defaultdict(list)
|
|
for bbox in bboxes:
|
|
if bbox[0] > -1 and bbox[1] > infer_config.draw_threshold:
|
|
result[bbox[0]].append({"score": bbox[1], "box": bbox[2:]})
|
|
return result
|
|
|
|
|
|
def detect_image(img_path):
|
|
infer_cfg = "model/object_det_model/infer_cfg.yml"
|
|
# load infer config
|
|
infer_config = PredictConfig(infer_cfg)
|
|
|
|
return predict_image(infer_config, PADDLE_DET, img_path)
|
|
|
|
|
|
def get_book_areas(image):
|
|
with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
|
|
cv2.imwrite(temp_file.name, image)
|
|
detect_result = detect_image(temp_file.name)
|
|
common_util.delete_temp_file(temp_file.name)
|
|
book_areas = detect_result[73]
|
|
result = []
|
|
for book_area in book_areas:
|
|
result.append(image_util.capture(image, book_area["box"]))
|
|
return result
|