File size: 3,185 Bytes
0a2675c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 |
from model1 import np, YOLO, processor, model
lp_detection = YOLO("models/yolov8n_lp_det.pt")
# processor = TrOCRProcessor.from_pretrained('models/processor')
# model = VisionEncoderDecoderModel.from_pretrained('models/model')
# set special tokens used for creating the decoder_input_ids from the labels
model.config.decoder_start_token_id = processor.tokenizer.cls_token_id
model.config.pad_token_id = processor.tokenizer.pad_token_id
# make sure vocab size is set correctly
model.config.vocab_size = model.config.decoder.vocab_size
# set beam search parameters
model.config.eos_token_id = processor.tokenizer.sep_token_id
model.config.max_length = 20
model.config.early_stopping = True
model.config.no_repeat_ngram_size = 3
model.config.length_penalty = 2.0
model.config.num_beams = 4
# function to detect licence plates in the given car images
def detect_lp(inputs):
lps = []
# running the license plate detection model with 50% confidence threshold
lp_results = lp_detection.predict(source=inputs, conf=0.5, verbose=False)
# iterating through each output (num of outputs will be same as num of inputs)
for lp_result in lp_results:
# finding the bounding boxes of the license plate detected
lp_boxes = lp_result.boxes.xyxy.tolist()
# iterating through each license plate detected
for lp_box in lp_boxes:
# cropping license plate image from the car image
lp = lp_result.orig_img[int(lp_box[1]):int(lp_box[3]), int(lp_box[0]):int(lp_box[2])]
lps.append(lp)
# breaking as we only want to detect one licence plate per car
break
# if no licence plate is detected then we are adding a black image
if len(lp_boxes) == 0:
lps.append(np.zeros((100,100,3), np.uint8))
return lps
# function to detect licence plate number in the given licence plate images
def detect_lp_text(inputs):
plate_number = []
# iterating through each licence plate
for input in inputs:
# finding the number/text in licence plate
pixel_values = processor(input, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
# if no text is found in the licence plate, then adding a default text not found
if len(generated_text) == 0:
plate_number.append("not found")
else:
# adding the licence plate number to a list
plate_number.append(generated_text)
return plate_number
def run(inputs):
# for future, to handle multiple inputs
# currently using just one input
inputs = inputs[0]
# detecting licence plates from the input images
# returns licence plate images, if it cant find a license plate a black image is returned
lps = detect_lp(inputs)
# detecting licence plate number from licence plate images
# returns text from the licence plate images, if none is detected "not found" text is returned
lp_text = detect_lp_text(lps)
return lps, lp_text
|