rk3588 视频类型判断 超分

import os
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
# from rknnpool import rknnPoolExecutor

import platform
from rknnlite.api import RKNNLite


from rknnpool import rknnPoolExecutor
from func import myFunc

# decice tree for RK356x/RK3588
DEVICE_COMPATIBLE_NODE = '/proc/device-tree/compatible'

RK3588_RKNN_MODEL = '/home/tyzc/RK_NPU_SDK_1.5.0/rknn-toolkit2/examples/onnx/yolov5/yolov5s_640_640_cut.rknn'
IMG_PATH = '/home/tyzc/RK_NPU_SDK_1.5.0/rknn-toolkit2/examples/onnx/yolov5/bus.jpg'
DATASET = '/home/tyzc/RK_NPU_SDK_1.5.0/rknn-toolkit2/examples/onnx/yolov5/dataset.txt'


OBJ_THRESH = 0.25
NMS_THRESH = 0.45
IMG_SIZE_HEIGHT = 640
IMG_SIZE_WEIGHT = 640
IMG_SIZE = 640

CLASSES = ("person", "cartoon")
video_path = "/home/tyzc/0416_syl_chaofen/rknn-multi-threaded-Super-Resolution-syl/cartorn/1怀旧动漫社聪明的一休_360_640.mp4"
cap = cv2.VideoCapture(video_path)
modelPath = "/home/tyzc/0416_syl_chaofen/rknn-multi-threaded-Super-Resolution-syl/rknnModel/32_1_16_4channel_123conv_1rdb1_net_oneresize_no_convhr_360_320_20240407_36.0778.rknn"
modelPath_1 = "/home/tyzc/0416_syl_chaofen/rknn-multi-threaded-Super-Resolution-syl/rknnModel/mix_0925/mix_32_1_16_4channel_123conv_1rdb1_net_oneresize_no_convhr_360_320_31.15..rknn"
# modelPath_1 = "/home/tyzc/0416_syl_chaofen/rknn-multi-threaded-Super-Resolution-syl/rknnModel/32_1_16_4channel_123conv_1rdb1_net_oneresize_no_convhr_360_320_20240407_36.0778.rknn"

width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
print("视频分辨率：{} x {}".format(height, width))
# modelPath = "/home/tyzc/Downloads/rknn-toolkit2-master/rknn-multi-threaded-nosigmoid/rknnModel/8_1_4/8_1_4_net_g_160000_Y_360_640_doqu.rknn"
# 线程数, 增大可提高帧率
TPEs = 6


# 初始化rknn池
  
pool = rknnPoolExecutor(
    rknnModel=modelPath,
    TPEs=TPEs,
    func=myFunc)
pool_1 = rknnPoolExecutor(
    rknnModel=modelPath,
    TPEs=TPEs,
    func=myFunc)

def sigmoid(x):
    return 1 / (1 + np.exp(-x))


def xywh2xyxy(x):
    # Convert [x, y, w, h] to [x1, y1, x2, y2]
    y = np.copy(x)
    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
    return y


def process(input, mask, anchors):

    anchors = [anchors[i] for i in mask]
    grid_h, grid_w = map(int, input.shape[0:2])

    box_confidence = sigmoid(input[..., 4])
    box_confidence = np.expand_dims(box_confidence, axis=-1)

    box_class_probs = sigmoid(input[..., 5:])

    box_xy = sigmoid(input[..., :2])*2 - 0.5

    col = np.tile(np.arange(0, grid_w), grid_w).reshape(-1, grid_w)
    row = np.tile(np.arange(0, grid_h).reshape(-1, 1), grid_h)
    col = col.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2)
    row = row.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2)
    grid = np.concatenate((col, row), axis=-1)
    box_xy += grid
    box_xy *= int(IMG_SIZE/grid_h)

    box_wh = pow(sigmoid(input[..., 2:4])*2, 2)
    box_wh = box_wh * anchors

    box = np.concatenate((box_xy, box_wh), axis=-1)

    return box, box_confidence, box_class_probs


def filter_boxes(boxes, box_confidences, box_class_probs):
    """Filter boxes with box threshold. It's a bit different with origin yolov5 post process!

    # Arguments
        boxes: ndarray, boxes of objects.
        box_confidences: ndarray, confidences of objects.
        box_class_probs: ndarray, class_probs of objects.

    # Returns
        boxes: ndarray, filtered boxes.
        classes: ndarray, classes for boxes.
        scores: ndarray, scores for boxes.
    """
    boxes = boxes.reshape(-1, 4)
    box_confidences = box_confidences.reshape(-1)
    box_class_probs = box_class_probs.reshape(-1, box_class_probs.shape[-1])

    _box_pos = np.where(box_confidences >= OBJ_THRESH)
    boxes = boxes[_box_pos]
    box_confidences = box_confidences[_box_pos]
    box_class_probs = box_class_probs[_box_pos]

    class_max_score = np.max(box_class_probs, axis=-1)
    classes = np.argmax(box_class_probs, axis=-1)
    _class_pos = np.where(class_max_score >= OBJ_THRESH)

    boxes = boxes[_class_pos]
    classes = classes[_class_pos]
    scores = (class_max_score* box_confidences)[_class_pos]

    return boxes, classes, scores


def nms_boxes(boxes, scores):
    """Suppress non-maximal boxes.

    # Arguments
        boxes: ndarray, boxes of objects.
        scores: ndarray, scores of objects.

    # Returns
        keep: ndarray, index of effective boxes.
    """
    x = boxes[:, 0]
    y = boxes[:, 1]
    w = boxes[:, 2] - boxes[:, 0]
    h = boxes[:, 3] - boxes[:, 1]

    areas = w * h
    order = scores.argsort()[::-1]

    keep = []
    while order.size > 0:
        i = order[0]
        keep.append(i)

        xx1 = np.maximum(x[i], x[order[1:]])
        yy1 = np.maximum(y[i], y[order[1:]])
        xx2 = np.minimum(x[i] + w[i], x[order[1:]] + w[order[1:]])
        yy2 = np.minimum(y[i] + h[i], y[order[1:]] + h[order[1:]])

        w1 = np.maximum(0.0, xx2 - xx1 + 0.00001)
        h1 = np.maximum(0.0, yy2 - yy1 + 0.00001)
        inter = w1 * h1

        ovr = inter / (areas[i] + areas[order[1:]] - inter)
        inds = np.where(ovr <= NMS_THRESH)[0]
        order = order[inds + 1]
    keep = np.array(keep)
    return keep


def yolov5_post_process(input_data):
    masks = [[0, 1, 2], [3, 4, 5], [6, 7, 8]]
    anchors = [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45],
               [59, 119], [116, 90], [156, 198], [373, 326]]

    boxes, classes, scores = [], [], []
    for input, mask in zip(input_data, masks):
        b, c, s = process(input, mask, anchors)
        b, c, s = filter_boxes(b, c, s)
        boxes.append(b)
        classes.append(c)
        scores.append(s)

    boxes = np.concatenate(boxes)
    boxes = xywh2xyxy(boxes)
    classes = np.concatenate(classes)
    scores = np.concatenate(scores)

    nboxes, nclasses, nscores = [], [], []
    for c in set(classes):
        inds = np.where(classes == c)
        b = boxes[inds]
        c = classes[inds]
        s = scores[inds]

        keep = nms_boxes(b, s)

        nboxes.append(b[keep])
        nclasses.append(c[keep])
        nscores.append(s[keep])

    if not nclasses and not nscores:
        return None, None, None

    boxes = np.concatenate(nboxes)
    classes = np.concatenate(nclasses)
    scores = np.concatenate(nscores)

    return boxes, classes, scores


def draw(image, boxes, scores, classes):
    """Draw the boxes on the image.

    # Argument:
        image: original image.
        boxes: ndarray, boxes of objects.
        classes: ndarray, classes of objects.
        scores: ndarray, scores of objects.
        all_classes: all classes name.
    """
    for box, score, cl in zip(boxes, scores, classes):
        top, left, right, bottom = box
        print('class: {}, score: {}'.format(CLASSES[cl], score))
        print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, bottom))
        top = int(top)
        left = int(left)
        right = int(right)
        bottom = int(bottom)

        cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 2)
        cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),
                    (top, left - 6),
                    cv2.FONT_HERSHEY_SIMPLEX,
                    0.6, (0, 0, 255), 2)


def letterbox(im, new_shape=(640, 640), color=(0, 0, 0)):
    # Resize and pad image while meeting stride-multiple constraints
    shape = im.shape[:2]  # current shape [height, width]
    if isinstance(new_shape, int):
        new_shape = (new_shape, new_shape)

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])

    # Compute padding
    ratio = r, r  # width, height ratios
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding

    dw /= 2  # divide padding into 2 sides
    dh /= 2

    if shape[::-1] != new_unpad:  # resize
        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return im, ratio, (dw, dh)


def get_host():
    # get platform and device type
    system = platform.system()
    machine = platform.machine()
    os_machine = system + '-' + machine
    if os_machine == 'Linux-aarch64':
        try:
            with open(DEVICE_COMPATIBLE_NODE) as f:
                device_compatible_str = f.read()
                if 'rk3588' in device_compatible_str:
                    host = 'RK3588'
                elif 'rk3562' in device_compatible_str:
                    host = 'RK3562'
                else:
                    host = 'RK3566_RK3568'
        except IOError:
            print('Read device node {} failed.'.format(DEVICE_COMPATIBLE_NODE))
            exit(-1)
    else:
        host = os_machine
    return host


if __name__ == '__main__':
    
    # Get device information
    host_name = get_host()
    if host_name == 'RK3588':
        rknn_model = RK3588_RKNN_MODEL
    else:
        print("This demo cannot run on the current platform: {}".format(host_name))
        exit(-1)

    rknn_lite = RKNNLite()
    # Load RKNN model
    print('--> Load RKNN model')
    ret = rknn_lite.load_rknn(rknn_model)
    if ret != 0:
        print('Load RKNN model failed')
        exit(ret)
    print('done')
    # Init runtime environment
    print('--> Init runtime environment')
    # run on RK356x/RK3588 with Debian OS, do not need specify target.
    if host_name == 'RK3588':
        # For RK3588, specify which NPU core the model runs on through the core_mask parameter.
        ret = rknn_lite.init_runtime(core_mask=RKNNLite.NPU_CORE_0_1_2)
        # ret = rknn_lite.init_runtime()
    else:
        ret = rknn_lite.init_runtime()
    if ret != 0:
        print('Init runtime environment failed')
        exit(ret)
    print('done')



    frames, loopTime, initTime = 0, time.time(), time.time()
    all_read_time = 0 
    all_show_time = 0
    person_num = 0
    cartoon_num = 0
    while (cap.isOpened()):
        if person_num + cartoon_num <= 10:
            real_time_start = time.time()
            # all_read_time = all_read_time + (read_time_2 - read_time_1) 
            frames += 1
            ret, frame = cap.read()
            frame_h, frame_w, c = frame.shape
            
            if not ret:
                break       
            # Set inputs
            img = frame
            # img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE, IMG_SIZE))
            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
            img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))

            # Inference
            print('--> Running model')
            # outputs = rknn_lite.inference(inputs=[img], data_format=['nchw'])
            inference_time_start = time.time()
            outputs = rknn_lite.inference(inputs=[img])
            inference_time_end = time.time()
            print("-" * 60)
            print(img.shape)
            print(inference_time_end - inference_time_start)

            # post process
            input0_data = outputs[0]
            input1_data = outputs[1]
            input2_data = outputs[2]

            input0_data = input0_data.reshape([3, -1]+list(input0_data.shape[-2:]))
            input1_data = input1_data.reshape([3, -1]+list(input1_data.shape[-2:]))
            input2_data = input2_data.reshape([3, -1]+list(input2_data.shape[-2:]))

            input_data = list()
            input_data.append(np.transpose(input0_data, (2, 3, 0, 1)))
            input_data.append(np.transpose(input1_data, (2, 3, 0, 1)))
            input_data.append(np.transpose(input2_data, (2, 3, 0, 1)))

            boxes, classes, scores = yolov5_post_process(input_data)

            img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
            # 统计0和1的数目
            if boxes is not None:
                count_0 = np.count_nonzero(classes == 0)
                count_1 = np.count_nonzero(classes == 1)
                person_num = person_num + count_0
                cartoon_num = cartoon_num + count_1
                draw(img_1, boxes, scores, classes)
                # cv2.imwrite('result.jpg', img_1)
            # 释放资源
            show_time_1 = time.time()

            # 设置文字、字体、大小、颜色等
            text = "person_num: " + str(person_num) + "  " + 'cartoon_num: ' + str(cartoon_num)
            org = (50, 100)  # 文字放置的坐标 (x, y)
            font = cv2.FONT_HERSHEY_SIMPLEX  # 字体类型
            font_scale = 1.0  # 字体大小
            color = (0, 0, 255)  # 文字颜色，白色 (B, G, R)
            thickness = 2  # 文字线条粗细

            frame_resize_show = cv2.resize(frame, (frame.shape[1] * 2, frame.shape[0] * 2), 2, 2)
            # 在图片上写文字
            cv2.putText(frame_resize_show, text, org, font, font_scale, color, thickness)

            cv2.imshow('test', frame_resize_show)
            show_time_2 = time.time()
            if cv2.waitKey(1) & 0xFF == ord('q'):
                # out.release()
                break
            print("person_num: " + str(person_num) + "  " + 'cartoon_num: ' + str(cartoon_num))
            real_time_end = time.time()
            print("-"*24)
            print(real_time_end - real_time_start) 
        else:
            rknn_lite.release()
            if cartoon_num > person_num:
                # 初始化异步所需要的帧
                pool_frames = []
                if (cap.isOpened()):
                    for i in range(TPEs + 1):
                        ret, frame = cap.read()
                        frame_cf = frame[:,:320,]
                        frame_resize = frame[:,320:,]
                        if not ret:
                            cap.release()
                            del pool
                            exit(-1)
                        pool_frames.append(frame_resize)
                        pool.put(frame_cf)
                while True:
                    frames += 1
                    ret, frame = cap.read()
                    if not ret:
                        break  
                    frame_resize = frame[:,:320,]
                    frame_cf = frame[:,320:,]
                    read_time_2 = time.time()     
            
                    if frames % 100000000 == 0:
                        # 调整图像大小
                        frame = cv2.resize(frame, (frame.shape[1] * 2, frame.shape[0] * 2), 2, 2)
                    else:
                        pool.put(frame_cf)
                        pool_frames.append(frame_resize)
                        frame_cf, flag = pool.get()
                        frame_resize = cv2.resize(pool_frames.pop(0), (frame.shape[1], frame.shape[0] * 2), 2, 2)
                        # 创建一个空白帧，大小与输入视频相同
                        result_frame = np.zeros((height*2, width*2, 3), dtype=np.uint8)
                        # 将左半部分放置在左边
                        result_frame[:, :width] = frame_resize
                        # 将右半部分放置在右边
                        result_frame[:, width:] = frame_cf
                        result_frame[:, width:width+1, :] = (255, 255, 255)
                        frame = result_frame
                        if flag == False:
                            break
                        show_time_1 = time.time()
                        # 设置文字、字体、大小、颜色等
                        text = "is_cartoon"
                        org = (50, 100)  # 文字放置的坐标 (x, y)
                        font = cv2.FONT_HERSHEY_SIMPLEX  # 字体类型
                        font_scale = 1.0  # 字体大小
                        color = (0, 0, 255)  # 文字颜色，白色 (B, G, R)
                        thickness = 2  # 文字线条粗细

                        # 在图片上写文字
                        cv2.putText(frame, text, org, font, font_scale, color, thickness)
                        cv2.imshow('test', frame)
                        show_time_2 = time.time()
                        if cv2.waitKey(1) & 0xFF == ord('q'):
                            # out.release()
                            break

                        if frames % 30 == 0:
                            print("30帧平均帧率:\t", 30 / (time.time() - loopTime - all_read_time - all_show_time), "帧")
                            loopTime = time.time()
                            all_read_time = 0 
                            all_show_time = 0
                        
            elif person_num > cartoon_num:
                # 初始化异步所需要的帧
                pool_frames = []
                if (cap.isOpened()):
                    for i in range(TPEs + 1):
                        ret, frame = cap.read()
                        frame_cf = frame[:,:320,]
                        frame_resize = frame[:,320:,]
                        if not ret:
                            cap.release()
                            del pool
                            exit(-1)
                        pool_frames.append(frame_resize)
                        pool_1.put(frame_cf)
                while True:
                    frames += 1
                    ret, frame = cap.read()
                    if not ret:
                        break  

                    frame_resize = frame[:,:320,]
                    frame_cf = frame[:,320:,]
                    read_time_2 = time.time()     
            
                    if frames % 100000000 == 0:
                        # 调整图像大小
                        frame = cv2.resize(frame, (frame.shape[1] * 2, frame.shape[0] * 2), 2, 2)
                    else:
                        pool_1.put(frame_cf)
                        pool_frames.append(frame_resize)
                        frame_cf, flag = pool_1.get()
                        frame_resize = cv2.resize(pool_frames.pop(0), (frame.shape[1], frame.shape[0] * 2), 2, 2)
                        # 创建一个空白帧，大小与输入视频相同
                        result_frame = np.zeros((height*2, width*2, 3), dtype=np.uint8)

                        # 将左半部分放置在左边
                        result_frame[:, :width] = frame_resize
                        # 将右半部分放置在右边
                        result_frame[:, width:] = frame_cf
                        result_frame[:, width:width+1, :] = (255, 255, 255)
                        frame = result_frame
                        if flag == False:
                            break
                        show_time_1 = time.time()
                        # 设置文字、字体、大小、颜色等
                        text = "is_person"
                        org = (50, 100)  # 文字放置的坐标 (x, y)
                        font = cv2.FONT_HERSHEY_SIMPLEX  # 字体类型
                        font_scale = 1.0  # 字体大小
                        color = (0, 0, 255)  # 文字颜色，白色 (B, G, R)
                        thickness = 2  # 文字线条粗细
                        # 在图片上写文字
                        cv2.putText(frame, text, org, font, font_scale, color, thickness)
                        cv2.imshow('test', frame)
                        show_time_2 = time.time()
                        if cv2.waitKey(1) & 0xFF == ord('q'):
                            # out.release()
                            break

                        if frames % 30 == 0:
                            print("30帧平均帧率:\t", 30 / (time.time() - loopTime - all_read_time - all_show_time), "帧")
                            loopTime = time.time()
                            all_read_time = 0 
                            all_show_time = 0
    print("总平均帧率\t", frames / (time.time() - initTime))
    # 释放cap和rknn线程池
    cap.release()
    # out.release()
    cv2.destroyAllWindows()
    pool_1.release()
    pool.release()