我有一个pytorch模型(包含shufflenetV2), 转换为onnx
使用 0_import_model.sh时，会提示 Do not support shape > 4。但不会出错，能成功生成json, data文件。
使用1_quantize_model.sh，会提示Do not support shape > 4。且报错，详细日志如下。
请问如何解决此错误？现在SDK支持pytorch shufflenetV2吗？
I Fitting image with scale.
I Channel mean value [127.5, 127.5, 127.5, 127.5]
I [TRAINER]Quantization start…
[TRAINER]Quantization start…
I Init validate tensor provider.
I Enqueue samples 1
I Init provider with 1 samples.
D set up a quantize net
D Process input_256 …
D Acuity output shape(input): (1 320 320 3)
D Real output shape: (1, 320, 320, 3)
D Process Conv_475_215 …
D Acuity output shape(convolution): (1 160 160 24)
D Real output shape: (1, 160, 160, 24)
D Process Relu_477_212 …
D Acuity output shape(relu): (1 160 160 24)
D Real output shape: (1, 160, 160, 24)
D Process MaxPool_478_209 …
D Acuity output shape(pooling): (1 80 80 24)
D Real output shape: (1, 80, 80, 24)
D Process Conv_479_206 …
D Acuity output shape(convolution): (1 40 40 24)
D Real output shape: (1, 40, 40, 24)
D Process Conv_481_202 …
D Acuity output shape(convolution): (1 40 40 24)
D Real output shape: (1, 40, 40, 24)
D Process Relu_483_198 …
D Acuity output shape(relu): (1 40 40 24)
D Real output shape: (1, 40, 40, 24)
D Process Conv_484_213 …
D Acuity output shape(convolution): (1 80 80 24)
D Real output shape: (1, 80, 80, 24)
D Process Relu_486_210 …
D Acuity output shape(relu): (1 80 80 24)
D Real output shape: (1, 80, 80, 24)
D Process Conv_487_207 …
D Acuity output shape(convolution): (1 40 40 24)
D Real output shape: (1, 40, 40, 24)
D Process Conv_489_203 …
D Acuity output shape(convolution): (1 40 40 24)
D Real output shape: (1, 40, 40, 24)
D Process Relu_491_199 …
D Acuity output shape(relu): (1 40 40 24)
D Real output shape: (1, 40, 40, 24)
D Process Concat_492_194 …
D Acuity output shape(concat): (1 40 40 48)
D Real output shape: (1, 40, 40, 48)
D Process Reshape_494_190_acuity_mark_perm_286 …
D Acuity output shape(permute): (1 48 40 40)
D Real output shape: (1, 48, 40, 40)
D Process Reshape_494_190 …
W Do not support shape > 4.
D Acuity output shape(reshape): (1 2 24 40 40)
D Real output shape: (1, 2, 24, 40, 40)
D Process Transpose_495_186 …
D Acuity output shape(permute): (1 24 2 40 40)
D Real output shape: (1, 24, 2, 40, 40)
D Process Reshape_497_182 …
D Acuity output shape(reshape): (1 48 40 40)
D Real output shape: (1, 48, 40, 40)
D Process Split_498_179 …
D Acuity output shape(split): (1 24 40 40) (1 24 40 40)
D Real output shape: (1, 24, 40, 40) (1, 24, 40, 40)
D Process Conv_500_176_acuity_mark_perm_300 …
D Acuity output shape(permute): (1 40 40 24)
D Real output shape: (1, 40, 40, 24)
D Process Conv_500_176 …
Traceback (most recent call last):
File “tensorzonex.py”, line 446, in
File “tensorzonex.py”, line 383, in main
File “acuitylib/app/tensorzone/quantization.py”, line 156, in run
File “acuitylib/app/tensorzone/quantization.py”, line 103, in _run_quantization
File “acuitylib/app/tensorzone/workspace.py”, line 172, in _setup_graph
File “acuitylib/app/tensorzone/graph.py”, line 59, in generate
File “acuitylib/acuitynetbuilder.py”, line 274, in build
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 301, in build_layer
File “acuitylib/acuitynetbuilder.py”, line 305, in build_layer
File “acuitylib/layer/acuitylayer.py”, line 262, in compute_shape
File “acuitylib/layer/convolution.py”, line 62, in compute_out_shape
AttributeError: ‘NoneType’ object has no attribute ‘format’
[4384] Failed to execute script tensorzonex