T ValueError: need more than 1 value to unpack

[复制链接] · 发表于 2019-4-19 15:48:26

转换一个caffe模型，提示T ValueError: need more than 1 value to unpack

详细的信息:
I Build complete.
I Initialzing network optimizer by Default ...
D Optimizing network with add_extra_io, format_input_ops, auto_fill_zero_bias, conv_kernel_transform, twod_op_transform, conv_1xn_transform, strip_op, extend_add_to_conv2d, extend_fc_to_conv2d, extend_unstack_split, extend_batchnormalize, swapper, merge_layer, transform_layer, proposal_opt, broadcast_op, strip_op, auto_fill_reshape_zero, adjust_output_attrs
E Catch exception when building RKNN model!
T Traceback (most recent call last):
T File "rknn/api/rknn_base.py", line 476, in rknn.api.rknn_base.RKNNBase.build
T File "rknn/api/rknn_base.py", line 405, in rknn.api.rknn_base.RKNNBase._build
T File "rknn/base/ovxconfiggenerator.py", line 177, in rknn.base.ovxconfiggenerator.generate_vx_config_from_files
T File "rknn/base/RKNNlib/app/helper/striphelper.py", line 56, in rknn.base.RKNNlib.app.helper.striphelper.StripHelper.build_network_2
T File "rknn/base/RKNNlib/app/helper/striphelper.py", line 86, in rknn.base.RKNNlib.app.helper.striphelper.StripHelper.build_netdict
T File "rknn/base/RKNNlib/optimize/optimizer.py", line 177, in rknn.base.RKNNlib.optimize.optimizer.Optimizer.apply
T File "rknn/base/RKNNlib/optimize/rules/conv_kernel_transform.py", line 191, in rknn.base.RKNNlib.optimize.rules.conv_kernel_transform.ConvKernelTransform.apply
T File "rknn/base/RKNNlib/optimize/rules/conv_kernel_transform.py", line 184, in rknn.base.RKNNlib.optimize.rules.conv_kernel_transform.ConvKernelTransform._check_and_process
T File "rknn/base/RKNNlib/optimize/rules/conv_kernel_transform.py", line 118, in rknn.base.RKNNlib.optimize.rules.conv_kernel_transform.ConvKernelTransform._check_asymmetric_kernel_pad
T ValueError: need more than 1 value to unpack