rknn-toolkit
rknn-toolkit copied to clipboard
Published
20 hours ago •
rockchip-linux
rockchip-linux
pytorch convert rknn rv1109 Error
import os
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
from rknn.api import RKNN
PT_MODEL = 'vd1_exp61_320x192.pt'
RKNN_MODEL = 'vd1_exp61_320x192.rknn'
IMG_PATH = './test.jpg'
DATASET = './dataset.txt'
QUANTIZE_ON = False
BOX_THRESH = 0.3
NMS_THRESH = 0.6
IMG_SIZE = (320, 192) # (width, height), such as (1280, 736)
CLASSES = ("car")
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_h).reshape(-1, grid_w)
row = np.tile(np.arange(0, grid_h).reshape(-1, 1), grid_w)
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[1]/grid_h), int(IMG_SIZE[0]/grid_w))
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.
"""
box_classes = np.argmax(box_class_probs, axis=-1)
box_class_scores = np.max(box_class_probs, axis=-1)
pos = np.where(box_confidences[...,0] >= BOX_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] - 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]]
anchor = [[20,13], [47,28], [66,52],
[84,76], [90,87], [141,113],
[191,155], [255,123], [251,184]]
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)
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN(verbose=False)
if not os.path.exists(PT_MODEL):
print('model not exist')
exit(-1)
_force_builtin_perm = False
# pre-process config
print('--> Config model')
rknn.config(
reorder_channel='0 1 2',
mean_values=[[0, 0, 0]],
std_values=[[255, 255, 255]],
optimization_level=3,
target_platform = 'rv1109',
quantize_input_node= QUANTIZE_ON,
output_optimize=1,
force_builtin_perm=_force_builtin_perm)
print('done')
# Load ONNX model
print('--> Loading model')
ret = rknn.load_pytorch(model=PT_MODEL, input_size_list=[[3,IMG_SIZE[1], IMG_SIZE[0]]])
if ret != 0:
print('Load yolov5 failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=QUANTIZE_ON, dataset=DATASET, pre_compile=False)
if ret != 0:
print('Build yolov5 failed!')
exit(ret)
print('done')
# Export RKNN model
print('--> Export RKNN model')
ret = rknn.export_rknn(RKNN_MODEL)
if ret != 0:
print('Export yolov5rknn failed!')
exit(ret)
print('done')
# init runtime environment
print('--> Init runtime environment')
ret = rknn.init_runtime(target='rv1109', device_id='0', rknn2precompile=True)
# ret = rknn.init_runtime('rk1808', device_id='1808')
if ret != 0:
print('Init runtime environment failed')
exit(ret)
print('done')
ret = rknn.export_rknn_precompile_model('./inference.rknn')
# Set inputs
img = cv2.imread(IMG_PATH)
img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE[1], IMG_SIZE[0]))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# Inference
print('--> Running model')
outputs = rknn.inference(inputs=[img], inputs_pass_through=[0 if not _force_builtin_perm else 1])
# 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)
if boxes is not None:
draw(img_1, boxes, scores, classes)
cv2.imshow("post process result", img_1)
cv2.waitKeyEx(0)
rknn.release()
=============================
(rknn) root@AI-S005:/home/rknn_convert_model/aiwinn/yolo1# python onnx.py
Traceback (most recent call last):
File "onnx.py", line 222, in <module>
rknn = RKNN(verbose=False)
File "/root/anaconda3/envs/rknn/lib/python3.6/site-packages/rknn/api/rknn.py", line 68, in __init__
self.config()
File "/root/anaconda3/envs/rknn/lib/python3.6/site-packages/rknn/api/rknn.py", line 732, in config
return self.rknn_base.config(args)
File "rknn/api/rknn_base.py", line 74, in rknn.api.rknn_base.RKNNBase.config
File "/root/anaconda3/envs/rknn/lib/python3.6/site-packages/rknn/base/acuitylib/__init__.py", line 1, in <module>
from acuitylib.optimize.optimizer import Optimizer
File "/root/anaconda3/envs/rknn/lib/python3.6/site-packages/rknn/base/acuitylib/__init__.py", line 1, in <module>
from acuitylib.optimize.optimizer import Optimizer
File "rknn/base/acuitylib/optimize/optimizer.py", line 14, in init rknn.base.acuitylib.optimize.optimizer
File "rknn/base/acuitylib/optimize/rules/merge_layer.py", line 3, in init rknn.base.acuitylib.optimize.rules.merge_layer
File "/root/anaconda3/envs/rknn/lib/python3.6/site-packages/rknn/base/acuitylib/layer/__init__.py", line 2, in <module>
from acuitylib.layer.add import *
File "rknn/base/acuitylib/layer/add.py", line 1, in init rknn.base.acuitylib.layer.add
File "rknn/base/acuitylib/layer/acuitylayer.py", line 9, in init rknn.base.acuitylib.layer.acuitylayer
File "rknn/base/acuitylib/core/tensor.py", line 16, in init rknn.base.acuitylib.core.tensor
File "rknn/base/acuitylib/core/type.py", line 4, in init rknn.base.acuitylib.core.type
ImportError: cannot import name TensorProto
Please do the RKNN model generate step on PC(x86) but not edge device. Do you mean the model transfer only be advised on PC??
I have tried the transfering code on RK3399 for several times, it works well sometimes, but sometimes failed..I felt confused...
