def rknn_convert(input_model, output_model, dataset_file, target_platform):
# Create RKNN object
rknn = RKNN()
print('--> config model')
rknn.config(channel_mean_value='127.5 127.5 127.5 127.5', reorder_channel='0 1 2', batch_size=1, target_platform=target_platform)
# Load onnx model
print('--> Loading model')
ret = rknn.load_onnx(model=input_model)
if ret != 0:
print('Load failed!')
exit(ret)
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset=dataset_file, pre_compile=True)
if ret != 0:
print('Build failed!')
exit(ret)
# Export rknn model
print('--> Export RKNN model')
ret = rknn.export_rknn(output_model)
if ret != 0:
print('Export .rknn failed!')
exit(ret)
# Release RKNN object
rknn.release()
def transfer(pb_path, rknn_name):
# Create RKNN object
rknn = RKNN()
# init runtime environment
print('--> Init runtime environment')
ret = rknn.init_runtime()
if ret != 0:
print('Init runtime environment failed')
exit(ret)
print('done')
# Config for Model Input PreProcess
rknn.config()
# Load TensorFlow Model
print('--> Loading model')
rknn.load_tensorflow(tf_pb=pb_path,
inputs=['Reshape'],
outputs=['probability'],
input_size_list=[[INPUT_WIDTH, INPUT_HEIGHT, 1]])
print('done')
# Build Model
print('--> Building model')
rknn.build(do_quantization=False)
print('done')
# Export RKNN Model
rknn.export_rknn(rknn_name)
# Release RKNN Context
rknn.release()
def convert_to_rknn():
from rknn.api import RKNN
# Create RKNN object
rknn = RKNN(verbose=True)
# pre-process config
print('--> config model')
rknn.config(channel_mean_value='127.5 127.5 127.5 128',
reorder_channel='0 1 2')
print('done')
# Load onnx model
print('--> Loading model')
ret = rknn.load_onnx(model='lprnet.onnx')
if ret != 0:
print('Load model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=False, pre_compile=True, dataset='./data/dataset.txt')
if ret != 0:
print('Build model failed!')
exit(ret)
print('done')
# Export rknn model
print('--> Export RKNN model')
ret = rknn.export_rknn('./lprnet.rknn')
if ret != 0:
print('Export model failed!')
exit(ret)
print('done')
def quantify_transfer(pb_name, dataset_name, export_name):
ret = 0
print(pb_name, dataset_name, export_name)
rknn = RKNN()
rknn.config(channel_mean_value='',
reorder_channel='',
quantized_dtype='dynamic_fixed_point-8')
print('--> Loading model')
ret = rknn.load_tensorflow(tf_pb=pb_name,
inputs=['test/x'],
outputs=['test/hypothesis'],
input_size_list=[[1, 4]])
if ret != 0:
print('load_tensorflow error')
rknn.release()
return ret
print('done')
print('--> Building model')
rknn.build(do_quantization=True, dataset=dataset_name)
print('done')
# rknn 모델 파일 저장 내보내기
rknn.export_rknn(export_name)
# Release RKNN Context
rknn.release()
return ret
def quanlization_darknet_model(model_path,
weight_path,
dataset_txt,
is_quantization=True,
pre_compile=False):
# 创建RKNN执行对象
rknn = RKNN(verbose=True, verbose_file='verbose.log')
rknn.config(channel_mean_value='0 0 0 255',
reorder_channel='0 1 2',
batch_size=4)
flag = rknn.load_darknet(model=model_path, weight=weight_path)
# 后面不用修改
if flag == 0:
print('load_darknet success')
else:
print('load_darknet failure')
print('done')
# 创建解析pb模型
# do_quantization=False指定不进行量化
# 量化会减小模型的体积和提升运算速度，但是会有精度的丢失
print('--> Building model')
print(os.getcwd())
# flag = rknn.build(do_quantization=False)
if is_quantization == True:
flag = rknn.build(do_quantization=True,
dataset=dataset_txt,
pre_compile=pre_compile)
print('do quantization ')
# 导出保存rknn模型文件
save_rknn_path = model_dir + '/' + model_path.split('/')[-1].split(
'.')[0] + '_quan.rknn'
else:
flag = rknn.build(do_quantization=False)
print('not do quantization')
# 导出保存rknn模型文件
save_rknn_path = model_dir + '/' + model_path.split('/')[-1].split(
'.')[0] + '.rknn'
if flag == 0:
print('build success')
else:
print('build failure')
print('done')
flag = rknn.export_rknn(save_rknn_path)
if flag == 0:
print('export success')
else:
print('export failure')
print('done')
print(save_rknn_path)
# Release RKNN Context
rknn.release()
print('save_rknn_path:', save_rknn_path)
def to_rknn(pb_path, rknn_path):
rknn = RKNN(verbose=True)
rknn.config(channel_mean_value='0 0 0 1', reorder_channel='0 1 2')
# rknn.config(channel_mean_value='128 128 128 128', reorder_channel='0 1 2')
print('--> Loading model')
rknn.load_tensorflow(tf_pb=pb_path,
inputs=['Placeholder'],
outputs=['ConvPred/ConvPred'],
input_size_list=[[INPUT_HEIGHT, INPUT_WIDTH, 3]])
print('done')
print('--> Building model')
rknn.build(do_quantization=False, pre_compile=True)
print('done')
rknn.export_rknn(rknn_path)
def transfer(pb_path, rknn_name):
# 创建RKNN执行对象
#rknn = RKNN(verbose=True, verbose_file='./mini_XCEPTION_build.log')
rknn = RKNN()
# 配置模型输入，用于NPU对数据输入的预处理
# channel_mean_value='0 0 0 255'，那么模型推理时，将会对RGB数据做如下转换
# (R - 0)/255, (G - 0)/255, (B - 0)/255。推理时，RKNN模型会自动做均值和归一化处理
# reorder_channel=’0 1 2’用于指定是否调整图像通道顺序，设置成0 1 2即按输入的图像通道顺序不做调整
# reorder_channel=’2 1 0’表示交换0和2通道，如果输入是RGB，将会被调整为BGR。如果是BGR将会被调整为RGB
#图像通道顺序不做调整
#rknn.config(channel_mean_value='0 0 0 255', reorder_channel='0 1 2')
rknn.config(quantized_dtype='dynamic_fixed_point-8')
# 加载TensorFlow模型
# tf_pb='digital_gesture.pb'指定待转换的TensorFlow模型
# inputs指定模型中的输入节点
# outputs指定模型中输出节点
# input_size_list指定模型输入的大小
print('--> Loading model')
ret = rknn.load_tensorflow(tf_pb=pb_path,
inputs=['input_1'],
outputs=['predictions/Softmax'],
input_size_list=[[INPUT_WIDTH, INPUT_HEIGHT, 1]])
if ret != 0:
print('Load Model failed!')
exit(ret)
print('done')
# 创建解析pb模型
# do_quantization=False指定不进行量化
# 量化会减小模型的体积和提升运算速度，但是会有精度的丢失
print('--> Building model')
ret = rknn.build(do_quantization=False)
if ret != 0:
print('Build Model failed!')
exit(ret)
print('done')
# 导出保存rknn模型文件
print('--> Export RKNN model')
ret = rknn.export_rknn(rknn_name)
if ret != 0:
print('Export Model failed!')
exit(ret)
print('done')
# Release RKNN Context
rknn.release()
def caffe2rknn(caffe_proto,caffe_weight,rknn_model):
print("start export")
rknn=RKNN(verbose=True)
ret=rknn.load_caffe(model=caffe_proto,
proto="caffe",
blobs=caffe_weight)
rknn.config(channel_mean_value='127.5 127.5 127.5 128.0',
reorder_channel='2 1 0',
#reorder_channel='0 1 2',
#need_horizontal_merge=True
)
ret = rknn.build(do_quantization=False)
#ret = rknn.build(do_quantization=True)
ret=rknn.export_rknn(export_path=rknn_model)
print("export finished")
def to_rknn(pb_path, rknn_path):
rknn = RKNN(verbose=True)
rknn.config(channel_mean_value='127.5 127.5 127.5 127.5',
reorder_channel='2 1 0')
rknn.load_tensorflow(
tf_pb=pb_path,
inputs=['input_tensor'],
outputs=[
#'lanenet_model/vgg_backend/binary_seg/ArgMax',
'lanenet_model/vgg_frontend/vgg16_decode_module/binary_seg_decode/binary_final_logits/binary_final_logits', # Workaround RKNN 1.1.0 bug
#'lanenet_model/vgg_backend/binary_seg/Softmax',
'lanenet_model/vgg_backend/instance_seg/pix_embedding_conv/pix_embedding_conv'
],
input_size_list=[[256, 512, 3]])
rknn.build(do_quantization=False, dataset='./dataset.txt')
rknn.export_rknn(rknn_path)
def save_rknn(self,
rknnpath,
verbose=True,
verbose_file=None,
input_mean_value='0 0 0 1',
input_channels='0 1 2',
do_quantization=True,
pre_compile=True):
TMP_PB_PATH = './tmp.pb'
from rknn.api import RKNN
self.save_pb(TMP_PB_PATH)
rknn = RKNN(verbose=verbose, verbose_file=verbose_file)
print('--> config model')
rknn.config(channel_mean_value=input_mean_value,
reorder_channel=input_channels)
print('done')
print('--> Loading pb, input shape = ' + str([self.__input_shape]))
ret = rknn.load_tensorflow(tf_pb=TMP_PB_PATH,
inputs=[self.input.op.name],
outputs=[self.output.op.name],
input_size_list=[list(self.__input_shape)])
if ret != 0:
print('Load pb failed! Ret = {}'.format(ret))
exit(ret)
print('done')
print('--> Building model')
ret = rknn.build(do_quantization=do_quantization,
dataset='./rknn_quantization.txt',
pre_compile=pre_compile)
if ret != 0:
print('Build model failed!')
exit(ret)
print('done')
print('--> Export RKNN model')
ret = rknn.export_rknn(rknnpath)
if ret != 0:
print('Export rknn failed!')
exit(ret)
print('done')
rknn.release()
def rknn_convert(input_model, output_model, model_input_shape, output_tensor_num, dataset_file, target_platform):
# Create RKNN object
rknn = RKNN()
print('--> config model')
rknn.config(channel_mean_value='0 0 0 255', reorder_channel='0 1 2', batch_size=1, target_platform=target_platform)
# Load tensorflow model
print('--> Loading model')
if output_tensor_num == 1:
output_tensor_names = ['predict_conv/BiasAdd']
elif output_tensor_num == 2:
output_tensor_names = ['predict_conv_1/BiasAdd', 'predict_conv_2/BiasAdd']
elif output_tensor_num == 3:
output_tensor_names = ['predict_conv_1/BiasAdd', 'predict_conv_2/BiasAdd', 'predict_conv_3/BiasAdd']
else:
raise ValueError('invalid output tensor number ', output_tensor_num)
ret = rknn.load_tensorflow(tf_pb=input_model,
inputs=['image_input'],
outputs=output_tensor_names,
input_size_list=[model_input_shape+(3,)],
predef_file=None)
#ret = rknn.load_onnx(model=input_model)
if ret != 0:
print('Load failed!')
exit(ret)
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset=dataset_file, pre_compile=True)
if ret != 0:
print('Build failed!')
exit(ret)
# Export rknn model
print('--> Export RKNN model')
ret = rknn.export_rknn(output_model)
if ret != 0:
print('Export .rknn failed!')
exit(ret)
# Release RKNN object
rknn.release()
def keras_to_rknn(cfg_path, h5_path, darknet_path, rknn_path, dataset_path,
flag):
# ------------------------------------------------------#
# h5 -> darknet, 保存成.weights
# ------------------------------------------------------#
keras_loader = KerasParser(cfg_path, h5_path, darknet_path)
for block in keras_loader.block_gen:
if 'convolutional' in block['type']:
keras_loader.conv(block)
keras_loader.close()
# ------------------------------------------------------#
# darknet -> rknn， 保存成.rknn
# ------------------------------------------------------#
# Create RKNN object
rknn = RKNN()
# Load tensorflow model
print('--> Loading model')
rknn.load_darknet(model=cfg_path, weight=darknet_path)
print('done')
rknn.config(channel_mean_value='0 0 0 255',
reorder_channel='0 1 2',
batch_size=1)
# Build model
print('--> Building model')
if flag:
rknn.build(do_quantization=True,
dataset=dataset_path,
pre_compile=True)
else:
rknn.build(do_quantization=False, pre_compile=True)
print('done')
# export model
print('--> Export model')
rknn.export_rknn(rknn_path)
print('done')
def rknn_convert(input_model, output_model, model_input_shape, dataset_file,
target_platform):
# Create RKNN object
rknn = RKNN()
print('--> config model')
rknn.config(channel_mean_value='0 0 0 255',
reorder_channel='0 1 2',
batch_size=1,
target_platform=target_platform)
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_tensorflow(tf_pb=input_model,
inputs=['image_input'],
outputs=['dense/Softmax'],
input_size_list=[model_input_shape + (3, )],
predef_file=None)
#ret = rknn.load_onnx(model=input_model)
if ret != 0:
print('Load failed!')
exit(ret)
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True,
dataset=dataset_file,
pre_compile=True)
if ret != 0:
print('Build failed!')
exit(ret)
# Export rknn model
print('--> Export RKNN model')
ret = rknn.export_rknn(output_model)
if ret != 0:
print('Export .rknn failed!')
exit(ret)
# Release RKNN object
rknn.release()
from rknn.api import RKNN
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN()
# Load tensorflow model
print('--> Loading model')
rknn.load_darknet(model='./yolov3.cfg', weight="./yolov3.weights")
#rknn.load_darknet(model='./yolov3-tiny.cfg', weight="./yolov3-tiny.weights")
print('done')
rknn.config(channel_mean_value='0 0 0 255',
reorder_channel='0 1 2',
batch_size=1)
# Build model
print('--> Building model')
#rknn.build(do_quantization=True, dataset='./dataset.txt')
rknn.build(do_quantization=True, dataset='./dataset_608x608.txt')
print('done')
#rknn.export_rknn('./yolov3_tiny.rknn')
rknn.export_rknn('./yolov3.rknn')
#rknn.load_rknn('./yolov3.rknn')
#image = Image.open('./dog.jpg').resize((416, 416))
#rknn.eval_perf(inputs=[image], is_print=True)
def show_perfs(perfs):
perfs = 'perfs: {}\n'.format(outputs)
print(perfs)
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN(verbose=False)
# pre-process config
print('--> config model')
rknn.config(channel_mean_value='103.94 116.78 123.68 58.82',
reorder_channel='0 1 2',
quantized_dtype='asymmetric_quantized-u8')
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_tflite(
model='../../tflite/mobilenet_v1/mobilenet_v1.tflite')
if ret != 0:
print('Load mobilenet_v1 failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True,
from rknn.api import RKNN
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN()
# Set model config
print('--> Config model')
rknn.config(mean_values=[[127.5, 127.5, 127.5]],
std_values=[[127.5, 127.5, 127.5]],
reorder_channel='0 1 2',
batch_size=16)
print('done')
# Hybrid quantization step2
print('--> hybrid_quantization_step2')
ret = rknn.hybrid_quantization_step2(
model_input='./ssd_mobilenet_v2.json',
data_input='./ssd_mobilenet_v2.data',
model_quantization_cfg='./ssd_mobilenet_v2.quantization.cfg',
dataset='./dataset.txt')
if ret != 0:
print('hybrid_quantization_step2 failed!')
exit(ret)
print('done')
# Export RKNN model
print('--> Export RKNN model')
ret = rknn.export_rknn('./ssd_mobilenet_v2.rknn')
if ret != 0:
import numpy as np
import cv2
from rknn.api import RKNN
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN()
# Set model config
print('--> Config model')
rknn.config(mean_values=[[127.5, 127.5, 127.5]],
std_values=[[127.5, 127.5, 127.5]],
reorder_channel='0 1 2',
quantized_dtype='asymmetric_quantized-u8',
batch_size=16)
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_tensorflow(
tf_pb='./ssd_mobilenet_v2.pb',
inputs=['FeatureExtractor/MobilenetV2/MobilenetV2/input'],
outputs=['concat_1', 'concat'],
input_size_list=[[300, 300, 3]],
predef_file=None)
if ret != 0:
print('Load model failed!')
exit(ret)
print('done')
yolo_type = 'tiny' if len(sys.argv) < 2 else sys.argv[1]
shutil.copy("settings_%s.py" % yolo_type, "settings.py")
if __name__ == '__main__':
from rknn.api import RKNN
from timeit import default_timer as timer
from settings import yolov3_weights, yolov3_model_cfg, rknn_model, \
pre_compile
# Create RKNN object
total_timer = timer()
rknn = RKNN()
# pre-process config
print('--> config model')
rknn.config(channel_mean_value='103.94 116.78 123.68 58.82',
reorder_channel='0 1 2')
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_darknet(model=yolov3_model_cfg, weight=yolov3_weights)
if ret != 0:
raise Exception('Load darknet yolov3 failed!')
print('done')
# Build model
print('--> Building model')
build_timer = timer()
# ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
# do_quantization:是否对模型进行量化,值为 True 或 False。
ret = rknn.build(do_quantization=False, pre_compile=pre_compile)
w = max(0, xmax - xmin)
h = max(0, ymax - ymin)
area = w * h
if area > 0:
return True
return False
if __name__ == "__main__":
VIDEO_PATH = sys.argv[1]
# Create RKNN object
rknn = RKNN(verbose=True)
# pre-process config
print('--> config model')
rknn.config(reorder_channel='0 1 2', channel_mean_value='0 0 0 255')
print('done')
if NEED_BUILD_MODEL:
# Load pytorch model
print('--> Loading model {}'.format(MODEL))
ret = rknn.load_darknet(model='/home/labasus/DataDisk/luqiao/deep_sort_yolov3/yolov3.cfg', weight=MODEL)
# ret = rknn.load_onnx(model=MODEL)
if ret != 0:
print('Load model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
ONNX_MODEL = './onnx_models/yolov5s_rm_transpose.onnx'
# platform="rk1808"
platform = "rv1109"
RKNN_MODEL = 'yolov5s_relu_{}_out_opt.rknn'.format(platform)
if __name__ == '__main__':
add_perm = False # 如果设置成True,则将模型输入layout修改成NHWC
# Create RKNN object
rknn = RKNN(verbose=True)
# pre-process config
print('--> config model')
rknn.config(batch_size=1, mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], reorder_channel='0 1 2', target_platform=[platform],
force_builtin_perm=add_perm, output_optimize=1)
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_onnx(model=ONNX_MODEL)
if ret != 0:
print('Load resnet50v2 failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
print('Build resnet50 failed!')
import numpy as np
import cv2
from rknn.api import RKNN
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN()
# pre-process config
print('--> config model')
rknn.config(channel_mean_value='127.5 127.5 127.5 128',
reorder_channel='2 1 0',
quantized_dtype='dynamic_fixed_point-8')
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_caffe(model='./ONet.prototxt',
proto='caffe',
blobs='./ONet.caffemodel')
if ret != 0:
print('Load model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset_onet.txt')
if ret != 0:
print('Build model failed!')
b[idx] = label_colors[l, 2]
rgb = np.stack([r, g, b], axis=2)
return rgb
if __name__ == '__main__':
export_mxnet_model()
# Create RKNN object
rknn = RKNN()
# pre-process config
print('--> Config model')
rknn.config(mean_values=[[123.675, 116.28, 103.53]], std_values=[[57.63, 57.63, 57.63]], reorder_channel='0 1 2')
print('done')
# Load mxnet model
symbol = './fcn_resnet101_voc-symbol.json'
params = './fcn_resnet101_voc-0000.params'
input_size_list = [[3, 480, 480]]
print('--> Loading model')
ret = rknn.load_mxnet(symbol, params, input_size_list)
if ret != 0:
print('Load mxnet model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
import numpy as np
import cv2
from rknn.api import RKNN
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN()
# pre-process config
print('--> config model')
rknn.config(channel_mean_value='0 0 0 1', reorder_channel='2 1 0')
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_caffe(model='./deploy.prototxt',
proto='caffe',
blobs='./solver_iter_45.caffemodel')
if ret != 0:
print('Load interp_test failed! Ret = {}'.format(ret))
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
print('Build interp_test failed!')
exit(ret)
print('done')
return np.exp(x)/sum(np.exp(x))
if __name__ == '__main__':
export_pytorch_model()
model = './resnet18.pt'
input_size_list = [[3,224,224]]
# Create RKNN object
rknn = RKNN()
# pre-process config
print('--> config model')
rknn.config(channel_mean_value='123.675 116.28 103.53 58.395', reorder_channel='0 1 2')
print('done')
# Load pytorch model
print('--> Loading model')
ret = rknn.load_pytorch(model=model, input_size_list=input_size_list)
if ret != 0:
print('Load pytorch model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
print('Build pytorch failed!')
import numpy as np
import cv2
from rknn.api import RKNN
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN()
# pre-process config
print('--> config model')
rknn.config(mean_values=[[0, 0, 0]],
std_values=[[1, 1, 1]],
reorder_channel='2 1 0')
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_caffe(model='./deploy.prototxt',
proto='caffe',
blobs='./solver_iter_45.caffemodel')
if ret != 0:
print('Load interp_test failed! Ret = {}'.format(ret))
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
print('Build interp_test failed!')
if value > 0:
topi = '{}: {}\n'.format(index[j], value)
else:
topi = '-1: 0.0\n'
top5_str += topi
print(top5_str)
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN()
# pre-process config
print('--> config model')
rknn.config(channel_mean_value='127.5 127.5 127.5 127.5', reorder_channel='0 1 2')
print('done')
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_tflite(model='./mobilenet_v1.tflite')
if ret != 0:
print('Load mobilenet_v1 failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt', pre_compile=False)
if ret != 0:
print('Build mobilenet_v1 failed!')
if __name__ == '__main__':
if not os.path.exists('./VGG_VOC0712_SSD_300x300_iter_120000.caffemodel'):
print('!!! Missing VGG_VOC0712_SSD_300x300_iter_120000.caffemodel !!!\n' \
'1. Download models_VGGNet_VOC0712_SSD_300x300.tar.gz from https://drive.google.com/file/d/0BzKzrI_SkD1_WVVTSmQxU0dVRzA/view\n' \
'2. Extract the VGG_VOC0712_SSD_300x300_iter_120000.caffemodel from models_VGGNet_VOC0712_SSD_300x300.tar.gz\n' \
'3. Or you can also download caffemodel from https://eyun.baidu.com/s/3jJhPRzo , password is rknn\n')
exit(-1)
# Create RKNN object
rknn = RKNN(verbose=False)
# Set model config
print('--> Config model')
rknn.config(mean_values=[[103.94, 116.78, 123.68]],
std_values=[[1, 1, 1]],
reorder_channel='2 1 0')
print('done')
# Load caffe model
print('--> Loading model')
ret = rknn.load_caffe(
model='./deploy_rm_detection_output.prototxt',
proto='caffe',
blobs='./VGG_VOC0712_SSD_300x300_iter_120000.caffemodel')
if ret != 0:
print('Load model failed! Ret = {}'.format(ret))
exit(ret)
print('done')
# Build model
def convert_model(model_path, out_path, pre_compile):
if os.path.isfile(model_path):
yaml_config_file = model_path
model_path = os.path.dirname(yaml_config_file)
else:
yaml_config_file = os.path.join(model_path, 'model_config.yml')
if not os.path.exists(yaml_config_file):
print('model config % not exist!' % yaml_config_file)
exit(-1)
model_configs = parse_model_config(yaml_config_file)
exported_rknn_model_path_list = []
for model_name in model_configs['models']:
model = model_configs['models'][model_name]
rknn = RKNN()
rknn.config(**model['configs'])
print('--> Loading model...')
if model['platform'] == 'tensorflow':
model_file_path = os.path.join(model_path,
model['model_file_path'])
input_size_list = []
for input_size_str in model['subgraphs']['input-size-list']:
input_size = list(map(int, input_size_str.split(',')))
input_size_list.append(input_size)
pass
rknn.load_tensorflow(tf_pb=model_file_path,
inputs=model['subgraphs']['inputs'],
outputs=model['subgraphs']['outputs'],
input_size_list=input_size_list)
elif model['platform'] == 'tflite':
model_file_path = os.path.join(model_path,
model['model_file_path'])
rknn.load_tflite(model=model_file_path)
elif model['platform'] == 'caffe':
prototxt_file_path = os.path.join(model_path,
model['prototxt_file_path'])
caffemodel_file_path = os.path.join(model_path,
model['caffemodel_file_path'])
rknn.load_caffe(model=prototxt_file_path,
proto='caffe',
blobs=caffemodel_file_path)
elif model['platform'] == 'onnx':
model_file_path = os.path.join(model_path,
model['model_file_path'])
rknn.load_onnx(model=model_file_path)
else:
print("platform %s not support!" % (model['platform']))
print('done')
if model['quantize']:
dataset_path = os.path.join(model_path, model['dataset'])
else:
dataset_path = './dataset'
print('--> Build RKNN model...')
rknn.build(do_quantization=model['quantize'],
dataset=dataset_path,
pre_compile=pre_compile)
print('done')
export_rknn_model_path = "%s.rknn" % (os.path.join(
out_path, model_name))
print('--> Export RKNN model to: {}'.format(export_rknn_model_path))
rknn.export_rknn(export_path=export_rknn_model_path)
exported_rknn_model_path_list.append(export_rknn_model_path)
print('done')
return exported_rknn_model_path_list
else:
topi = '-1: 0.0\n'
top5_str += topi
print(top5_str)
if __name__ == '__main__':
export_keras_model()
# Create RKNN object
rknn = RKNN()
# pre-process config
print('--> config model')
rknn.config(mean_values=[[127.5, 127.5, 127.5]], std_values=[[127.5, 127.5, 127.5]], reorder_channel='0 1 2')
print('done')
# Load keras model
print('--> Loading model')
ret = rknn.load_keras(model=KERAS_MODEL_PATH)
if ret != 0:
print('Load keras model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
print('Build pytorch failed!')
default=1,
help='batch size')
opt = parser.parse_args()
ONNX_MODEL = opt.onnx
if opt.rknn:
RKNN_MODEL = opt.rknn
else:
RKNN_MODEL = "%s.rknn" % os.path.splitext(ONNX_MODEL)[0]
rknn = RKNN()
print('--> config model')
if opt.original:
rknn.config(mean_values=[[
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
]],
std_values=[[
255.0, 255.0, 255.0, 255.0, 255.0, 255.0, 255.0, 255.0,
255.0, 255.0, 255.0, 255.0
]],
batch_size=opt.batch_size,
target_platform="rk3399pro") # reorder_channel='0 1 2',
else:
rknn.config(channel_mean_value='0 0 0 255',
reorder_channel='2 1 0',
batch_size=opt.batch_size,
target_platform="rk3399pro")
# Load tensorflow model
print('--> Loading model')
ret = rknn.load_onnx(model=ONNX_MODEL)
assert ret == 0, "Load onnx failed!"
# Build model
print('--> Building model')
