214332 - rpi5 aidge

MODEL : DSCNN.onnx

===============
ONNX Graph
===============

input_1 ['unk__123', 49, 10, 1]

===============
Aidge Graph
===============

  Node(name='functional_1_dense_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__121', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_4_Relu;functional_1_batch_normalization_4_FusedBatchNormV3;functional_1_conv2d_2_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_2_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_2_Conv2D1', optype='Conv2D', parents: [1, 1, 1], children: [[1]])
  Node(name='functional_1_conv2d_1_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_4_Conv2D_dequant', optype='Dequantizer', parents: [1], children: [[1]])
  Node(name='functional_1_activation_Relu;functional_1_batch_normalization_FusedBatchNormV3;functional_1_conv2d_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_Conv2D1', optype='PaddedConv2D', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='functional_1_activation_6_Relu;functional_1_batch_normalization_6_FusedBatchNormV3;functional_1_conv2d_3_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_3_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_3_Conv2D1', optype='Conv2D', parents: [1, 1, 1], children: [[1]])
  Node(name='functional_1_activation_7_Relu;functional_1_batch_normalization_7_FusedBatchNormV3;functional_1_depthwise_conv2d_3_depthwise;functional_1_depthwise_conv2d_3_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_3_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_2_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_8_Relu;functional_1_batch_normalization_8_FusedBatchNormV3;functional_1_conv2d_4_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_4_BiasAdd;functional_1_conv2d_4_Conv2D1', optype='Conv2D', parents: [1, 1, 1], children: [[1]])
  Node(name='Relu__11', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_activation_2_Relu;functional_1_batch_normalization_2_FusedBatchNormV3;functional_1_conv2d_1_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_1_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_1_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_dense_BiasAdd', optype='MatMul', parents: [1, 1], children: [[1]])
  Node(name='functional_1_conv2d_4_Conv2D', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__122', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__120', optype='Producer', children: [[1]])
  Node(name='Relu__17', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_activation_8_Relu;functional_1_batch_normalization_8_FusedBatchNormV3;functional_1_conv2d_4_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_4_BiasAdd;functional_1_conv2d_4_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_1_Conv2D_dequant', optype='Dequantizer', parents: [1], children: [[1]])
  Node(name='Relu__23', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_activation_4_Relu;functional_1_batch_normalization_4_FusedBatchNormV3;functional_1_conv2d_2_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_2_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_2_Conv2D', optype='Producer', children: [[1]])
  Node(name='Relu__29', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_activation_5_Relu;functional_1_batch_normalization_5_FusedBatchNormV3;functional_1_depthwise_conv2d_2_depthwise;functional_1_depthwise_conv2d_2_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_2_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='functional_1_flatten_Reshape', optype='Reshape', parents: [1, 1], children: [[1]])
  Node(name='functional_1_average_pooling2d_AvgPool', optype='AvgPooling2D', parents: [1], children: [[1]])
  Node(name='new_shape__107', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_1_Relu;functional_1_batch_normalization_1_FusedBatchNormV3;functional_1_depthwise_conv2d_depthwise;functional_1_depthwise_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__109', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_3_Relu;functional_1_batch_normalization_3_FusedBatchNormV3;functional_1_depthwise_conv2d_1_depthwise;functional_1_depthwise_conv2d_1_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_1_BiasAdd_ReadVariableOp_resource1', optype='PaddedConvDepthWise2D', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='functional_1_conv2d_2_Conv2D_dequant', optype='Dequantizer', parents: [1], children: [[1]])
  Node(name='const_fold_opt__110', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_5_Relu;functional_1_batch_normalization_5_FusedBatchNormV3;functional_1_depthwise_conv2d_2_depthwise;functional_1_depthwise_conv2d_2_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_2_BiasAdd_ReadVariableOp_resource1', optype='PaddedConvDepthWise2D', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='Relu__5', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_activation_1_Relu;functional_1_batch_normalization_1_FusedBatchNormV3;functional_1_depthwise_conv2d_depthwise;functional_1_depthwise_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_BiasAdd_ReadVariableOp_resource1', optype='PaddedConvDepthWise2D', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='Identity', optype='Softmax', parents: [1], children: [[]])
  Node(name='const_fold_opt__117', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_2_Relu;functional_1_batch_normalization_2_FusedBatchNormV3;functional_1_conv2d_1_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_1_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_1_Conv2D1', optype='Conv2D', parents: [1, 1, 1], children: [[1]])
  Node(name='functional_1_activation_7_Relu;functional_1_batch_normalization_7_FusedBatchNormV3;functional_1_depthwise_conv2d_3_depthwise;functional_1_depthwise_conv2d_3_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_3_BiasAdd_ReadVariableOp_resource1', optype='PaddedConvDepthWise2D', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='functional_1_conv2d_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_Relu;functional_1_batch_normalization_FusedBatchNormV3;functional_1_conv2d_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_Conv2D1__45', optype='Reshape', parents: [0, 1], children: [[1]])
  Node(name='Add__33', optype='Add', parents: [1, 1], children: [[1]])
  Node(name='functional_1_activation_Relu;functional_1_batch_normalization_FusedBatchNormV3;functional_1_conv2d_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_Conv2D', optype='Producer', children: [[1]])
  Node(name='Relu__14', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_conv2d_Conv2D_dequant', optype='Dequantizer', parents: [1], children: [[1]])
  Node(name='Relu__20', optype='ReLU', parents: [1], children: [[1]])
  Node(name='Relu__8', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_conv2d_3_Conv2D_dequant', optype='Dequantizer', parents: [1], children: [[1]])
  Node(name='Relu__26', optype='ReLU', parents: [1], children: [[1]])
  Node(name='functional_1_activation_6_Relu;functional_1_batch_normalization_6_FusedBatchNormV3;functional_1_conv2d_3_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_3_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_3_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_3_Relu;functional_1_batch_normalization_3_FusedBatchNormV3;functional_1_depthwise_conv2d_1_depthwise;functional_1_depthwise_conv2d_1_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_1_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_3_Conv2D', optype='Producer', children: [[1]])

===============
Supported nodes
===============

Native operators: 51 (11 types)
- Add: 1
- AvgPooling2D: 1
- Conv2D: 4
- Dequantizer: 5
- MatMul: 1
- PaddedConv2D: 1
- PaddedConvDepthWise2D: 4
- Producer: 22
- ReLU: 9
- Reshape: 2
- Softmax: 1
Generic operators: 0 (0 types)
Native types coverage: 100.0% (11/11)
Native operators coverage: 100.0% (51/51)
  (defaultdict(<class 'int'>, {'Dequantizer': 5, 'Reshape': 2, 'AvgPooling2D': 1, 'Add': 1, 'MatMul': 1, 'Conv2D': 4, 'ReLU': 9, 'Producer': 22, 'PaddedConvDepthWise2D': 4, 'Softmax': 1, 'PaddedConv2D': 1}), defaultdict(<class 'int'>, {}))

===============\Graph manipulation
===============

Remove flatten
Fuse batchnorm
Expand metaop
Fuse to metaop

===============
New Aidge Graph
===============

  Node(name='', optype='PadConvDwAct', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='functional_1_activation_1_Relu;functional_1_batch_normalization_1_FusedBatchNormV3;functional_1_depthwise_conv2d_depthwise;functional_1_depthwise_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__121', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_4_Conv2D_dequant_CastIn', optype='Cast', parents: [1], children: [[1]])
  Node(name='functional_1_conv2d_4_Conv2D_dequant_SubDeQuant', optype='Sub', parents: [1, 1], children: [[1]])
  Node(name='functional_1_activation_Relu;functional_1_batch_normalization_FusedBatchNormV3;functional_1_conv2d_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_Conv2D1__45', optype='Reshape', parents: [0, 1], children: [[1]])
  Node(name='', optype='PadConvDwAct', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='', optype='PadConvDwAct', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='', optype='PadConvDwAct', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='functional_1_conv2d_Conv2D_dequant_CastIn', optype='Cast', parents: [1], children: [[1]])
  Node(name='ScalingFactor', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_2_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_dense_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_Conv2D_dequant_MulDeQuant', optype='Mul', parents: [1, 1], children: [[1]])
  Node(name='functional_1_flatten_Reshape', optype='Reshape', parents: [1, 1], children: [[1]])
  Node(name='ZeroPoint', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_Relu;functional_1_batch_normalization_FusedBatchNormV3;functional_1_conv2d_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_Conv2D', optype='Producer', children: [[1]])
  Node(name='ScalingFactor', optype='Producer', children: [[1]])
  Node(name='Identity', optype='Softmax', parents: [1], children: [[]])
  Node(name='functional_1_conv2d_4_Conv2D', optype='Producer', children: [[1]])
  Node(name='new_shape__107', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_Conv2D_dequant_SubDeQuant', optype='Sub', parents: [1, 1], children: [[1]])
  Node(name='const_fold_opt__110', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_3_Relu;functional_1_batch_normalization_3_FusedBatchNormV3;functional_1_depthwise_conv2d_1_depthwise;functional_1_depthwise_conv2d_1_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_1_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='functional_1_activation_2_Relu;functional_1_batch_normalization_2_FusedBatchNormV3;functional_1_conv2d_1_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_1_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_1_Conv2D', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__122', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_1_Conv2D_dequant_CastIn', optype='Cast', parents: [1], children: [[1]])
  Node(name='functional_1_activation_7_Relu;functional_1_batch_normalization_7_FusedBatchNormV3;functional_1_depthwise_conv2d_3_depthwise;functional_1_depthwise_conv2d_3_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_3_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='ScalingFactor_2', optype='Producer', children: [[1]])
  Node(name='Add__33', optype='Add', parents: [1, 1], children: [[1]])
  Node(name='functional_1_activation_8_Relu;functional_1_batch_normalization_8_FusedBatchNormV3;functional_1_conv2d_4_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_4_BiasAdd;functional_1_conv2d_4_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_1_Conv2D_dequant_MulDeQuant', optype='Mul', parents: [1, 1], children: [[1]])
  Node(name='ZeroPoint_2', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__120', optype='Producer', children: [[1]])
  Node(name='', optype='PadConvAct', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
  Node(name='functional_1_conv2d_1_Conv2D', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_Conv2D', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__117', optype='Producer', children: [[1]])
  Node(name='', optype='ConvAct', parents: [1, 1, 1], children: [[1]])
  Node(name='ZeroPoint', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_1_Conv2D_dequant_SubDeQuant', optype='Sub', parents: [1, 1], children: [[1]])
  Node(name='', optype='ConvAct', parents: [1, 1, 1], children: [[1]])
  Node(name='functional_1_conv2d_2_Conv2D_dequant_CastIn', optype='Cast', parents: [1], children: [[1]])
  Node(name='functional_1_activation_4_Relu;functional_1_batch_normalization_4_FusedBatchNormV3;functional_1_conv2d_2_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_2_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_2_Conv2D', optype='Producer', children: [[1]])
  Node(name='ScalingFactor', optype='Producer', children: [[1]])
  Node(name='', optype='ConvAct', parents: [1, 1, 1], children: [[1]])
  Node(name='ZeroPoint', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_2_Conv2D_dequant_MulDeQuant', optype='Mul', parents: [1, 1], children: [[1]])
  Node(name='functional_1_activation_5_Relu;functional_1_batch_normalization_5_FusedBatchNormV3;functional_1_depthwise_conv2d_2_depthwise;functional_1_depthwise_conv2d_2_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_depthwise_conv2d_2_BiasAdd_ReadVariableOp_resource', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_2_Conv2D_dequant_SubDeQuant', optype='Sub', parents: [1, 1], children: [[1]])
  Node(name='functional_1_conv2d_3_Conv2D_dequant_CastIn', optype='Cast', parents: [1], children: [[1]])
  Node(name='functional_1_activation_6_Relu;functional_1_batch_normalization_6_FusedBatchNormV3;functional_1_conv2d_3_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_3_BiasAdd;functional_1_conv2d_4_Conv2D;functional_1_conv2d_3_Conv2D', optype='Producer', children: [[1]])
  Node(name='const_fold_opt__109', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_4_Conv2D_dequant_MulDeQuant', optype='Mul', parents: [1, 1], children: [[1]])
  Node(name='ScalingFactor_1', optype='Producer', children: [[1]])
  Node(name='functional_1_conv2d_3_Conv2D_dequant_MulDeQuant', optype='Mul', parents: [1, 1], children: [[1]])
  Node(name='ZeroPoint_1', optype='Producer', children: [[1]])
  Node(name='', optype='ConvAct', parents: [1, 1, 1], children: [[1]])
  Node(name='functional_1_average_pooling2d_AvgPool', optype='AvgPooling2D', parents: [1], children: [[1]])
  Node(name='functional_1_conv2d_3_Conv2D_dequant_SubDeQuant', optype='Sub', parents: [1, 1], children: [[1]])
  Node(name='functional_1_dense_BiasAdd', optype='MatMul', parents: [1, 1], children: [[1]])
  Node(name='functional_1_conv2d_3_Conv2D', optype='Producer', children: [[1]])

===============
Supported nodes 2
===============

Native operators: 62 (12 types)
- Add: 1
- AvgPooling2D: 1
- Cast: 5
- ConvAct: 4
- MatMul: 1
- Mul: 5
- PadConvAct: 1
- PadConvDwAct: 4
- Producer: 32
- Reshape: 2
- Softmax: 1
- Sub: 5
Generic operators: 0 (0 types)
Native types coverage: 100.0% (12/12)
Native operators coverage: 100.0% (62/62)
  (defaultdict(<class 'int'>, {'Producer': 32, 'ConvAct': 4, 'AvgPooling2D': 1, 'Sub': 5, 'MatMul': 1, 'Add': 1, 'PadConvDwAct': 4, 'Reshape': 2, 'Cast': 5, 'Softmax': 1, 'Mul': 5, 'PadConvAct': 1}), defaultdict(<class 'int'>, {}))

===============
Supported nodes
===============

Native operators: 62 (12 types)
- Add: 1
- AvgPooling2D: 1
- Cast: 5
- ConvAct: 4
- MatMul: 1
- Mul: 5
- PadConvAct: 1
- PadConvDwAct: 4
- Producer: 32
- Reshape: 2
- Softmax: 1
- Sub: 5
Generic operators: 0 (0 types)
Native types coverage: 100.0% (12/12)
Native operators coverage: 100.0% (62/62)
  (defaultdict(<class 'int'>, {'Producer': 32, 'PadConvDwAct': 4, 'MatMul': 1, 'Add': 1, 'AvgPooling2D': 1, 'ConvAct': 4, 'Softmax': 1, 'Reshape': 2, 'Cast': 5, 'Mul': 5, 'Sub': 5, 'PadConvAct': 1}), defaultdict(<class 'int'>, {}))

===============
Compile
===============

OK

===============
Create Scheduler
===============

OK

===============
Name nodes
===============

functional_1_conv2d_3_Conv2D (Producer)
functional_1_conv2d_1_Conv2D (Producer)
functional_1_conv2d_Conv2D (Producer)
_ConvAct_3_biases (Producer)
_PadConvDwAct_3_biases (Producer)
_ConvAct_2_biases (Producer)
_PadConvDwAct_2_biases (Producer)
_ConvAct_1_biases (Producer)
_PadConvDwAct_1_biases (Producer)
_ConvAct_0_biases (Producer)
functional_1_conv2d_4_Conv2D (Producer)
new_shape__107 (Producer)
functional_1_dense_BiasAdd_ReadVariableOp_resource (Producer)
functional_1_conv2d_2_Conv2D (Producer)
_PadConvDwAct_0_biases (Producer)
_PadConvAct_0_biases (Producer)
_PadConvDwAct_0_weights (Producer)
_PadConvDwAct_3_weights (Producer)
_PadConvDwAct_2_weights (Producer)
_PadConvDwAct_1_weights (Producer)
const_fold_opt__109 (Producer)
const_fold_opt__110 (Producer)
ZeroPoint (Producer)
ScalingFactor (Producer)
ZeroPoint_1 (Producer)
ScalingFactor_1 (Producer)
ZeroPoint (Producer)
ScalingFactor (Producer)
ZeroPoint_2 (Producer)
ScalingFactor_2 (Producer)
ZeroPoint (Producer)
ScalingFactor (Producer)
_Cast_0 (Cast)
_Cast_1 (Cast)
_Cast_2 (Cast)
_Cast_3 (Cast)
_Cast_4 (Cast)
_Reshape_0 (Reshape)
_Sub_0 (Sub)
_Sub_1 (Sub)
_Sub_2 (Sub)
_Sub_3 (Sub)
_Sub_4 (Sub)
_ConvAct_3_weights (Mul)
_ConvAct_2_weights (Mul)
_ConvAct_1_weights (Mul)
_ConvAct_0_weights (Mul)
_PadConvAct_0_weights (Mul)
_PadConvAct_0 (PadConvAct)
_PadConvDwAct_0 (PadConvDwAct)
_ConvAct_0 (ConvAct)
_PadConvDwAct_1 (PadConvDwAct)
_ConvAct_1 (ConvAct)
_PadConvDwAct_2 (PadConvDwAct)
_ConvAct_2 (ConvAct)
_PadConvDwAct_3 (PadConvDwAct)
_ConvAct_3 (ConvAct)
_AvgPooling2D_0 (AvgPooling2D)
_Reshape_1 (Reshape)
_MatMul_0 (MatMul)
_Add_0 (Add)
_Softmax_0 (Softmax)

===============
Set backend
===============

OK

===============
Set data format to NHWC if needed
===============

Is Layout fragil: True
⚠️ Keeping model in NCHW (layout fragile)
OK

===============
Forward dims
===============


===============
Regenerate scheduler
===============

OK

===============
Export model
===============

[NOTICE] - Node name "ZeroPoint" is a duplicate, renaming it to ZeroPoint_1.
[NOTICE] - Node name "ScalingFactor" is a duplicate, renaming it to ScalingFactor_1.
[NOTICE] - Node name "ZeroPoint" is a duplicate, renaming it to ZeroPoint_2.
[NOTICE] - Node name "ScalingFactor" is a duplicate, renaming it to ScalingFactor_2.
[NOTICE] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[WARNING] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[NOTICE] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[WARNING] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[NOTICE] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[WARNING] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[NOTICE] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[WARNING] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[WARNING] - Unable to forward dimensions (circular dependency and/or wrong dimensions and/or data
[WARNING]   dependent dimension?). Unable to compute output dims for nodes [" (ConvAct)", "
[WARNING]   (ConvAct)", " (ConvAct)", " (PadConvAct)", " (PadConvDwAct)", " (PadConvDwAct)", "
[WARNING]   (PadConvDwAct)",
[WARNING]   "functional_1_activation_Relu;functional_1_batch_normalization_FusedBatchNormV3;function
[WARNING]   l_1_conv2d_BiasAdd_ReadVariableOp_resource;functional_1_conv2d_BiasAdd;functional_1_conv
[WARNING]   d_4_Conv2D;functional_1_conv2d_Conv2D1__45 (Reshape)", "functional_1_flatten_Reshape
[WARNING]   (Reshape)", " (PadConvDwAct)", "functional_1_dense_BiasAdd (MatMul)", "Add__33 (Add)", "
[WARNING]   (ConvAct)"].
[NOTICE] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[ERROR] - Wrong input size ([1, 5, 66, 27]) for ConvDepthWise operator. Expected dims are [x, 64, x,
[ERROR]   x].
[ERROR] - Wrong input size ([1, 5, 66, 27]) for ConvDepthWise operator. Expected dims are [x, 64, x,
[ERROR]   x].
[WARNING] - Unable to forward dimensions (circular dependency and/or wrong dimensions and/or data
[WARNING]   dependent dimension?). Unable to compute output dims for nodes [" (ConvDepthWise2D)"].
[WARNING] - Unable to forward dimensions (circular dependency and/or wrong dimensions and/or data
[WARNING]   dependent dimension?). Unable to compute output dims for nodes [" (PadConvDw)"].
[WARNING] - Unable to forward dimensions (circular dependency and/or wrong dimensions and/or data
[WARNING]   dependent dimension?). Unable to compute output dims for nodes ["_ConvAct_3 (ConvAct)",
[WARNING]   "_PadConvDwAct_3 (PadConvDwAct)", "_PadConvDwAct_0 (PadConvDwAct)", "_ConvAct_0
[WARNING]   (ConvAct)", "_Reshape_1 (Reshape)", "_ConvAct_2 (ConvAct)", "_MatMul_0 (MatMul)",
[WARNING]   "_Add_0 (Add)", "_PadConvDwAct_1 (PadConvDwAct)", "_PadConvDwAct_2 (PadConvDwAct)",
[WARNING]   "_ConvAct_1 (ConvAct)"].
[ERROR] - Assertion failed: requiredSize.type == Elts_t::Data in /opt/aidge/aidge/aidge_core/src/scheduler/SequentialScheduler.cpp:786
[FATAL] - Cannot generate memory with token-based producer-consumer model for node _PadConvDwAct_0
[FATAL]   (of type PadConvDwAct). You may need to forward dimensions in the graph first.
Traceback (most recent call last):
  File "/app/AI_Project/01_generate_cpp.py", line 169, in <module>
    aidge_core.export_utils.scheduler_export(
  File "/opt/venv/lib/python3.10/site-packages/aidge_core/export_utils/scheduler_export.py", line 79, in scheduler_export
    peak_mem, mem_info = memory_manager(scheduler, **memory_manager_args)
  File "/opt/venv/lib/python3.10/site-packages/aidge_core/mem_info.py", line 306, in generate_optimized_memory_info
    mem_manager = scheduler.generate_memory(
RuntimeError: Cannot generate memory with token-based producer-consumer model for node _PadConvDwAct_0 (of type PadConvDwAct). You may need to forward dimensions in the graph first.
Error: export_model/data directory does not exist.

sed: can't read export_model/Makefile: No such file or directory
sed: can't read export_model/Makefile: No such file or directory
sed: can't read export_model/Makefile: No such file or directory
sed: can't read export_model/Makefile: No such file or directory
make: AI_Build AI_Deploy AI_Manager AI_Project AI_Support ConvNet.onnx DSCNN.onnx MLP_MNIST.onnx MobileNet-v2.onnx README.md __pycache__ config.json docker examples exit_functions.sh export_model mnist.onnx mnist_test_input_type2.bin model_1D_classifier.onnx model_type2.onnx print_raw_output.py type1_test.sh type2_test.sh type3_test.sh No targets specified and no makefile found. Stop.

null