infer_mnn.py 3.94 KB
import cv2
from PIL import Image, ImageFont, ImageDraw
import MNN
import numpy as np


def keep_shape_resize(frame, size=128):
    w, h = frame.size
    temp = max(w, h)
    mask = Image.new('RGB', (temp, temp), (0, 0, 0))
    if w >= h:
        position = (0, (w - h) // 2)
    else:
        position = ((h - w) // 2, 0)
    mask.paste(frame, position)
    mask = mask.resize((size, size))
    return mask


def image_infer_mnn(mnn_model_path, image_path, class_list):
    image = Image.open(image_path)
    input_image = keep_shape_resize(image)
    input_data = np.array(input_image).astype(np.float32).transpose((2, 0, 1)) / 255
    interpreter = MNN.Interpreter(mnn_model_path)
    session = interpreter.createSession()
    input_tensor = interpreter.getSessionInput(session)
    tmp_input = MNN.Tensor((1, 3, 128, 128), MNN.Halide_Type_Float, input_data, MNN.Tensor_DimensionType_Caffe)
    input_tensor.copyFrom(tmp_input)
    interpreter.runSession(session)
    infer_result = interpreter.getSessionOutput(session)
    output_data = infer_result.getData()
    out = output_data.index(max(output_data))
    draw = ImageDraw.Draw(image)
    font = ImageFont.truetype(r"C:\Windows\Fonts\BRITANIC.TTF", 35)
    draw.text((10, 10), class_list[int(out)], font=font, fill='red')
    return image


def video_infer_mnn(mnn_model_path, video_path):
    cap = cv2.VideoCapture(video_path)
    interpreter = MNN.Interpreter(mnn_model_path)
    session = interpreter.createSession()
    input_tensor = interpreter.getSessionInput(session)
    while True:
        _, frame = cap.read()
        if _:
            image_data = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            image_data = Image.fromarray(image_data)
            image_data = keep_shape_resize(image_data, 128)
            input_data = np.array(image_data).astype(np.float32).transpose((2, 0, 1)) / 255
            tmp_input = MNN.Tensor((1, 3, 128, 128), MNN.Halide_Type_Float, input_data, MNN.Tensor_DimensionType_Caffe)
            input_tensor.copyFrom(tmp_input)
            interpreter.runSession(session)
            infer_result = interpreter.getSessionOutput(session)
            output_data = infer_result.getData()
            out = output_data.index(max(output_data))
            cv2.putText(frame, class_list[int(out)], (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 0, 255), thickness=2)
            cv2.imshow('frame', frame)
            if cv2.waitKey(24) & 0XFF == ord('q'):
                break
        else:
            break


def camera_infer_mnn(mnn_model_path, camera_id):
    cap = cv2.VideoCapture(camera_id)
    interpreter = MNN.Interpreter(mnn_model_path)
    session = interpreter.createSession()
    input_tensor = interpreter.getSessionInput(session)
    while True:
        _, frame = cap.read()
        if _:
            image_data = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            image_data = Image.fromarray(image_data)
            image_data = keep_shape_resize(image_data, 128)
            input_data = np.array(image_data).astype(np.float32).transpose((2, 0, 1)) / 255
            tmp_input = MNN.Tensor((1, 3, 128, 128), MNN.Halide_Type_Float, input_data, MNN.Tensor_DimensionType_Caffe)
            input_tensor.copyFrom(tmp_input)
            interpreter.runSession(session)
            infer_result = interpreter.getSessionOutput(session)
            output_data = infer_result.getData()
            out = output_data.index(max(output_data))
            cv2.putText(frame, class_list[int(out)], (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 0, 255), thickness=2)
            cv2.imshow('frame', frame)
            if cv2.waitKey(24) & 0XFF == ord('q'):
                break
        else:
            break


if __name__ == '__main__':
    class_list = ['mask', 'no_mask']
    image_path = 'test_image/mask_2995.jpg'
    mnn_model_path = 'cls_abnormal_face_mnn_1.0.0_v0.0.1.mnn'
    # image
    image = image_infer_mnn(mnn_model_path, image_path, class_list)
    image.show()
    # camera
    # camera_infer_mnn(mnn_model_path,0)