Toybrick

标题: 转换yolov3按照官方教程执行报错 [打印本页]

作者: kwzs    时间: 2021-1-13 15:46
标题: 转换yolov3按照官方教程执行报错
执行python3 rknn_transform_416x416.py时报错:
使用的环境:rknn-toolkit   1.4.0

--> Loading model
E Catch exception when loading darknet model: ./yolov3_416x416.cfg!
E Traceback (most recent call last):
E   File "rknn/api/rknn_base.py", line 601, in rknn.api.rknn_base.RKNNBase.load_darknet
E   File "rknn/base/RKNNlib/converter/convert_darknet.py", line 754, in rknn.base.RKNNlib.converter.convert_darknet.Converter.load_blobs
E   File "rknn/base/RKNNlib/converter/convert_darknet.py", line 452, in rknn.base.RKNNlib.converter.convert_darknet.Convolution_Blob_Assign.assign
E   File "/usr/local/python3-rk/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 292, in reshape
E     return _wrapfunc(a, 'reshape', newshape, order=order)
E   File "/usr/local/python3-rk/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 56, in _wrapfunc
E     return getattr(obj, method)(*args, **kwds)
E ValueError: cannot reshape array of size 82766 into shape (256,128,3,3)
done
--> Building model
Traceback (most recent call last):
  File "rknn_transform_416x416.py", line 27, in <module>
    rknn.build(do_quantization=True, dataset='./dataset_416x416.txt', pre_compile=True)
  File "/usr/local/python3-rk/lib/python3.6/site-packages/rknn/api/rknn.py", line 231, in build
    inputs = self.rknn_base.net.get_input_layers()
AttributeError: 'NoneType' object has no attribute 'get_input_layers'


作者: kwzs    时间: 2021-1-14 15:45
我找到问题了  TMD我的weights文件只有五兆,我服了
作者: 钱钱钱    时间: 2022-3-8 14:22
麻烦博主能具体讲解一下是怎么解决吗?




欢迎光临 Toybrick (https://t.rock-chips.com/) Powered by Discuz! X3.3