895816513 发表于 2023-5-11 10:50
板子上难装rktoolkit，我之前装了好几次没装成功过。我看那CSDN博客也没说要运行什么demo。
大佬，请教一下，如果不在板子上安装rknn_toolkit，怎样调用API接口from rknn.api import RKNN？
我打算把opencv-python版本降低到4.0.1.23或者4.3.0.36再试试
我看csdn博主运行的代码
python3 rknn_camera_416x416.py
确实要安装rknn_toolkit，否则我这边无法调用这个接口；我原本想接入相机进行目标检测
import numpy as np
import cv2
from PIL import Image
from rknn.api import RKNN
from timeit import default_timer as timer
GRID0 = 13
GRID1 = 26import numpy as np
import cv2
from PIL import Image
from rknn.api import RKNN
from timeit import default_timer as timer
GRID0 = 13
GRID1 = 26
GRID2 = 52
LISTSIZE = 85
SPAN = 3
NUM_CLS = 80
MAX_BOXES = 500
OBJ_THRESH = 0.5
NMS_THRESH = 0.6
CLASSES = ("person", "bicycle", "car","motorbike ","aeroplane ","bus ","train","truck ","boat","traffic light",
"fire hydrant","stop sign ","parking meter","bench","bird","cat","dog ","horse ","sheep","cow","elephant",
"bear","zebra ","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite",
"baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife ",
"spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza ","donut","cake","chair","sofa",
"pottedplant","bed","diningtable","toilet ","tvmonitor","laptop ","mouse ","remote ","keyboard ","cell phone","microwave ",
"oven ","toaster","sink","refrigerator ","book","clock","vase","scissors ","teddy bear ","hair drier", "toothbrush ")
def sigmoid(x):
return 1 / (1 + np.exp(-x))
def process(input, mask, anchors):
anchors = [anchors[i] for i in mask]
grid_h, grid_w = map(int, input.shape[0:2])
box_confidence = input[..., 4]
obj_thresh = -np.log(1/OBJ_THRESH - 1)
pos = np.where(box_confidence > obj_thresh)
input = input[pos]
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])
box_wh = np.exp(input[..., 2:4])
for idx, val in enumerate(pos[2]):
box_wh[idx] = box_wh[idx] * anchors[pos[2][idx]]
pos0 = np.array(pos[0])[:, np.newaxis]
pos1 = np.array(pos[1])[:, np.newaxis]
grid = np.concatenate((pos1, pos0), axis=1)
box_xy += grid
box_xy /= (grid_w, grid_h)
box_wh /= (416, 416)
box_xy -= (box_wh / 2.)
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 object threshold.
# 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.
"""
box_scores = box_confidences * box_class_probs
box_classes = np.argmax(box_scores, axis=-1)
box_class_scores = np.max(box_scores, axis=-1)
pos = np.where(box_class_scores >= OBJ_THRESH)
boxes = boxes[pos]
classes = box_classes[pos]
scores = box_class_scores[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]
h = boxes[:, 3]
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 yolov3_post_process(input_data):
# # yolov3
# masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
# anchors = [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45],
# [59, 119], [116, 90], [156, 198], [373, 326]]
# yolov3-tiny
masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
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)
classes = np.concatenate(classes)
scores = np.concatenate(scores)
# # Scale boxes back to original image shape.
# width, height = 416, 416 #shape[1], shape[0]
# image_dims = [width, height, width, height]
# boxes = boxes * image_dims
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):
x, y, w, h = box
print('class: {}, score: {}'.format(CLASSES[cl], score))
print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(x, y, x+w, y+h))
x *= image.shape[1]
y *= image.shape[0]
w *= image.shape[1]
h *= image.shape[0]
top = max(0, np.floor(x + 0.5).astype(int))
left = max(0, np.floor(y + 0.5).astype(int))
right = min(image.shape[1], np.floor(x + w + 0.5).astype(int))
bottom = min(image.shape[0], np.floor(y + h + 0.5).astype(int))
# print('class: {}, score: {}'.format(CLASSES[cl], score))
# print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, 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)
# print('class: {0}, score: {1:.2f}'.format(CLASSES[cl], score))
# print('box coordinate x,y,w,h: {0}'.format(box))
def load_model():
rknn = RKNN()
print('-->loading model')
#rknn.load_rknn('./yolov3_tiny.rknn')
rknn.load_rknn('./yolov3_416x416.rknn')
print('loading model done')
print('--> Init runtime environment')
ret = rknn.init_runtime()
if ret != 0:
print('Init runtime environment failed')
exit(ret)
print('done')
return rknn
if __name__ == '__main__':
rknn = load_model()
font = cv2.FONT_HERSHEY_SIMPLEX;
#capture = cv2.VideoCapture("data/3.mp4")
capture = cv2.VideoCapture(0)
accum_time = 0
curr_fps = 0
prev_time = timer()
fps = "FPS: ??"
try:
while(True):
ret, frame = capture.read()
if ret == True:
image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, (416, 416))
testtime=timer()
out_boxes, out_boxes2, out_boxes3 = rknn.inference(inputs=[image])
testtime2=timer()
print("rknn use time {}", testtime2-testtime)
out_boxes = out_boxes.reshape(SPAN, LISTSIZE, GRID0, GRID0)
out_boxes2 = out_boxes2.reshape(SPAN, LISTSIZE, GRID1, GRID1)
out_boxes3 = out_boxes3.reshape(SPAN, LISTSIZE, GRID2, GRID2)
input_data = []
input_data.append(np.transpose(out_boxes, (2, 3, 0, 1)))
input_data.append(np.transpose(out_boxes2, (2, 3, 0, 1)))
input_data.append(np.transpose(out_boxes3, (2, 3, 0, 1)))
testtime=timer()
boxes, classes, scores = yolov3_post_process(input_data)
testtime2=timer()
print("process use time: {}", testtime2-testtime)
testtime=timer()
if boxes is not None:
draw(frame, boxes, scores, classes)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time += exec_time
curr_fps += 1
if accum_time > 1:
accum_time -= 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(frame, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.imshow("results", frame)
c = cv2.waitKey(5) & 0xff
if c == 27:
cv2.destroyAllWindows()
capture.release()
rknn.release()
break;
testtime2=timer()
print("show image use time: {}", testtime2-testtime)
except KeyboardInterrupt:
cv2.destroyAllWindows()
capture.release()
rknn.release()
SPAN = 3
NUM_CLS = 80
MAX_BOXES = 500
OBJ_THRESH = 0.5
NMS_THRESH = 0.6
CLASSES = ("person", "bicycle", "car","motorbike ","aeroplane ","bus ","train","truck ","boat","traffic light",
"fire hydrant","stop sign ","parking meter","bench","bird","cat","dog ","horse ","sheep","cow","elephant",
"bear","zebra ","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite",
"baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife ",
"spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza ","donut","cake","chair","sofa",
"pottedplant","bed","diningtable","toilet ","tvmonitor","laptop ","mouse ","remote ","keyboard ","cell phone","microwave ",
"oven ","toaster","sink","refrigerator ","book","clock","vase","scissors ","teddy bear ","hair drier", "toothbrush ")
def sigmoid(x):
return 1 / (1 + np.exp(-x))
def process(input, mask, anchors):
anchors = [anchors[i] for i in mask]
grid_h, grid_w = map(int, input.shape[0:2])
box_confidence = input[..., 4]
obj_thresh = -np.log(1/OBJ_THRESH - 1)
pos = np.where(box_confidence > obj_thresh)
input = input[pos]
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])
box_wh = np.exp(input[..., 2:4])
for idx, val in enumerate(pos[2]):
box_wh[idx] = box_wh[idx] * anchors[pos[2][idx]]
pos0 = np.array(pos[0])[:, np.newaxis]
pos1 = np.array(pos[1])[:, np.newaxis]
grid = np.concatenate((pos1, pos0), axis=1)
box_xy += grid
box_xy /= (grid_w, grid_h)
box_wh /= (416, 416)
box_xy -= (box_wh / 2.)
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 object threshold.
# 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.
"""
box_scores = box_confidences * box_class_probs
box_classes = np.argmax(box_scores, axis=-1)
box_class_scores = np.max(box_scores, axis=-1)
pos = np.where(box_class_scores >= OBJ_THRESH)
boxes = boxes[pos]
classes = box_classes[pos]
scores = box_class_scores[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]
h = boxes[:, 3]
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 yolov3_post_process(input_data):
# # yolov3
# masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
# anchors = [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45],
# [59, 119], [116, 90], [156, 198], [373, 326]]
# yolov3-tiny
masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
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)
classes = np.concatenate(classes)
scores = np.concatenate(scores)
# # Scale boxes back to original image shape.
# width, height = 416, 416 #shape[1], shape[0]
# image_dims = [width, height, width, height]
# boxes = boxes * image_dims
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):
x, y, w, h = box
print('class: {}, score: {}'.format(CLASSES[cl], score))
print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(x, y, x+w, y+h))
x *= image.shape[1]
y *= image.shape[0]
w *= image.shape[1]
h *= image.shape[0]
top = max(0, np.floor(x + 0.5).astype(int))
left = max(0, np.floor(y + 0.5).astype(int))
right = min(image.shape[1], np.floor(x + w + 0.5).astype(int))
bottom = min(image.shape[0], np.floor(y + h + 0.5).astype(int))
# print('class: {}, score: {}'.format(CLASSES[cl], score))
# print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, 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)
# print('class: {0}, score: {1:.2f}'.format(CLASSES[cl], score))
# print('box coordinate x,y,w,h: {0}'.format(box))
def load_model():
rknn = RKNN()
print('-->loading model')
#rknn.load_rknn('./yolov3_tiny.rknn')
rknn.load_rknn('./yolov3_416x416.rknn')
print('loading model done')
print('--> Init runtime environment')
ret = rknn.init_runtime()
if ret != 0:
print('Init runtime environment failed')
exit(ret)
print('done')
return rknn
if __name__ == '__main__':
rknn = load_model()
font = cv2.FONT_HERSHEY_SIMPLEX;
#capture = cv2.VideoCapture("data/3.mp4")
capture = cv2.VideoCapture(0)
accum_time = 0
curr_fps = 0
prev_time = timer()
fps = "FPS: ??"
try:
while(True):
ret, frame = capture.read()
if ret == True:
image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, (416, 416))
testtime=timer()
out_boxes, out_boxes2, out_boxes3 = rknn.inference(inputs=[image])
testtime2=timer()
print("rknn use time {}", testtime2-testtime)
out_boxes = out_boxes.reshape(SPAN, LISTSIZE, GRID0, GRID0)
out_boxes2 = out_boxes2.reshape(SPAN, LISTSIZE, GRID1, GRID1)
out_boxes3 = out_boxes3.reshape(SPAN, LISTSIZE, GRID2, GRID2)
input_data = []
input_data.append(np.transpose(out_boxes, (2, 3, 0, 1)))
input_data.append(np.transpose(out_boxes2, (2, 3, 0, 1)))
input_data.append(np.transpose(out_boxes3, (2, 3, 0, 1)))
testtime=timer()
boxes, classes, scores = yolov3_post_process(input_data)
testtime2=timer()
print("process use time: {}", testtime2-testtime)
testtime=timer()
if boxes is not None:
draw(frame, boxes, scores, classes)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time += exec_time
curr_fps += 1
if accum_time > 1:
accum_time -= 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(frame, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.imshow("results", frame)
c = cv2.waitKey(5) & 0xff
if c == 27:
cv2.destroyAllWindows()
capture.release()
rknn.release()
break;
testtime2=timer()
print("show image use time: {}", testtime2-testtime)
except KeyboardInterrupt:
cv2.destroyAllWindows()
capture.release()
rknn.release()
另外，我看快速上手文档和网页操作建议基于X86安装toolkit，但是很奇怪瑞芯微官方，也提供arm板子的toolkit安装包，而且博主居然安装成功！！！
