关于支持DenseNet模型/HarDNet模型

请问下能够添加DenseNet/HarDNet中的经典密集结构的支持吗？万分感谢！

一直都支持。
遇到转下不支持的OP把verbose log发出来

原来的模型中有41个concat操作，现在将模型concat操作数量降低到10个，可以正常运行了。后续硬件能够更新到大数量concat操作吗？

out = F.interpolate(input,size=(skip.size(2), skip.size(3)),mode="bilinear",align_corners=True,)
你们现在支持这个op吗？为啥我一加这个就直接跑不通了？

D Optimizing network with qnt_adjust_coef, multiply_transform, add_extra_io, format_input_ops, auto_fill_zero_bias, conv_kernel_transform, twod_op_transform, conv_1xn_transform, strip_op, extend_unstack_split, extend_batchnormalize, swapper, merge_layer, transform_layer, proposal_opt, broadcast_op, strip_op, auto_fill_reshape_zero, adjust_output_attrs
D Optimizing network with c2drv_convert_axis, c2drv_convert_shape, c2drv_convert_array, c2drv_cast_dtype
I Building data ...
I Packing data ...
D Packing convolution_at_input.1_2 ...
D Packing convolution_at_input_11.1_41 ...
D Packing convolution_at_input_14.1_28 ...
D Packing convolution_at_input_17.1_29 ...
D Packing convolution_at_input_2.1_82 ...
D Packing convolution_at_input_20.1_86 ...
D Packing convolution_at_input_24.1_62 ...
D Packing convolution_at_input_27.1_81 ...
D Packing convolution_at_input_30.1_63 ...
D Packing convolution_at_input_33.1_64 ...
D Packing convolution_at_input_36.1_95 ...
D Packing convolution_at_input_40.1_83 ...
D Packing convolution_at_input_43.1_94 ...
D Packing convolution_at_input_46.1_84 ...
D Packing convolution_at_input_49.1_85 ...
D Packing convolution_at_input_5.1_65 ...
D Packing convolution_at_input_52.1_61 ...
D Packing convolution_at_input_56.1_42 ...
D Packing convolution_at_input_59.1_30 ...
D Packing convolution_at_input_62.1_43 ...
D Packing convolution_at_input_65.1_31 ...
D Packing convolution_at_input_68.1_32 ...
D Packing convolution_at_input_72.1_13 ...
D Packing convolution_at_input_75.1_8 ...
D Packing convolution_at_input_78.1_9 ...
D Packing convolution_at_input_8.1_50 ...
I Build config finished.
done
--> Export RKNN model
done
--> Init runtime environment
D target set by user is: None
D Start ntp...
I npu_transfer_proxy pid: 1292, status: sleeping
D NPUTransfer: efuseid = 3399:30754ce228712a9b
I NPUTransfer: Starting NPU Transfer Client, Transfer version 1.9.8 (40e4a8a@2020-01-02T09:16:20)
D NPUTransfer: Transfer spec = local:transfer_proxy
D NPUTransfer: Transfer interface successfully opened, fd = 9
E RKNNAPI: rknn_init,  msg_load_ack fail, ack = 1(ACK_FAIL), expect 0(ACK_SUCC)!
E RKNNAPI: ==============================================
E RKNNAPI: RKNN VERSION:
E RKNNAPI:   API: 1.3.2 (9eebd73 build: 2020-04-02 15:30:36)
E RKNNAPI:   DRV: 1.3.0 (c4f8c23 build: 2019-11-25 10:39:29)
E RKNNAPI: ==============================================
D NPUTransfer: Transfer client closed, fd = 9
E Catch exception when init runtime!
E Traceback (most recent call last):
E   File "rknn/api/rknn_base.py", line 1067, in rknn.api.rknn_base.RKNNBase.init_runtime
E   File "rknn/api/rknn_runtime.py", line 326, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID