123868 - rpi4b aidge
123868 - rpi4b aidge
Summary: Pipeline succeeded and valid report was generated.
Model Details
- model name : mnist-7.onnx
- model url : Download here
Logs Details
user.log
MODEL : mnist7.onnx
===============
ONNX Graph
===============
Number of input = 9 is not supported (max 1)
Input3 [1, 1, 28, 28]
===============
Aidge Graph
===============
Node(name='Parameter88', optype='Producer', children: [[1]])
Node(name='ReLU114', optype='ReLU', parents: [1], children: [[1]])
Node(name='Parameter193_reshape1_shape', optype='Producer', children: [[1]])
Node(name='Parameter5', optype='Producer', children: [[1]])
Node(name='Parameter87', optype='Producer', children: [[1]])
Node(name='Convolution110', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='Pooling66', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='Times212', optype='MatMul', parents: [1, 1], children: [[1]])
Node(name='Times212_reshape0', optype='Reshape', parents: [1, 1], children: [[1]])
Node(name='Pooling160_Output_0_reshape0_shape', optype='Producer', children: [[1]])
Node(name='Plus112', optype='Add', parents: [1, 1], children: [[1]])
Node(name='Convolution28', optype='PaddedConv2D', parents: [0, 1, 0, 0, 0, 0], children: [[1]])
Node(name='Parameter6', optype='Producer', children: [[1]])
Node(name='Plus214', optype='Add', parents: [1, 1], children: [[]])
Node(name='Plus30', optype='Add', parents: [1, 1], children: [[1]])
Node(name='Pooling160', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='ReLU32', optype='ReLU', parents: [1], children: [[1]])
Node(name='Times212_reshape1', optype='Reshape', parents: [1, 1], children: [[1]])
Node(name='Parameter193', optype='Producer', children: [[1]])
Node(name='Parameter194', optype='Producer', children: [[1]])
===============
Supported nodes
===============
Native operators: 20 (7 types)
- Add: 3
- MatMul: 1
- MaxPooling2D: 2
- PaddedConv2D: 2
- Producer: 8
- ReLU: 2
- Reshape: 2
Generic operators: 0 (0 types)
Native types coverage: 100.0% (7/7)
Native operators coverage: 100.0% (20/20)
(defaultdict(<class 'int'>, {'Producer': 8, 'PaddedConv2D': 2, 'Add': 3, 'Reshape': 2, 'MaxPooling2D': 2, 'ReLU': 2, 'MatMul': 1}), defaultdict(<class 'int'>, {}))
===============\Graph manipulation
===============
Remove flatten
Fuse batchnorm
Expand metaop
Fuse to metaop
===============
New Aidge Graph
===============
Node(name='', optype='AddAct', parents: [1, 1], children: [[1]])
Node(name='Pooling160_Output_0_reshape0_shape', optype='Producer', children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='Times212', optype='MatMul', parents: [1, 1], children: [[1]])
Node(name='Parameter6', optype='Producer', children: [[1]])
Node(name='Parameter88', optype='Producer', children: [[1]])
Node(name='Times212_reshape1', optype='Reshape', parents: [1, 1], children: [[1]])
Node(name='Parameter193', optype='Producer', children: [[1]])
Node(name='', optype='PadConv', parents: [0, 1, 0, 0, 0, 0], children: [[1]])
Node(name='Pooling66', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='Parameter5', optype='Producer', children: [[1]])
Node(name='Parameter87', optype='Producer', children: [[1]])
Node(name='Parameter193_reshape1_shape', optype='Producer', children: [[1]])
Node(name='', optype='AddAct', parents: [1, 1], children: [[1]])
Node(name='Times212_reshape0', optype='Reshape', parents: [1, 1], children: [[1]])
Node(name='Plus214', optype='Add', parents: [1, 1], children: [[]])
Node(name='Pooling160', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='Parameter194', optype='Producer', children: [[1]])
===============
Supported nodes 2
===============
Native operators: 18 (7 types)
- Add: 1
- AddAct: 2
- MatMul: 1
- MaxPooling2D: 2
- PadConv: 2
- Producer: 8
- Reshape: 2
Generic operators: 0 (0 types)
Native types coverage: 100.0% (7/7)
Native operators coverage: 100.0% (18/18)
(defaultdict(<class 'int'>, {'Reshape': 2, 'AddAct': 2, 'MaxPooling2D': 2, 'Producer': 8, 'PadConv': 2, 'Add': 1, 'MatMul': 1}), defaultdict(<class 'int'>, {}))
===============
Supported nodes
===============
Native operators: 18 (7 types)
- Add: 1
- AddAct: 2
- MatMul: 1
- MaxPooling2D: 2
- PadConv: 2
- Producer: 8
- Reshape: 2
Generic operators: 0 (0 types)
Native types coverage: 100.0% (7/7)
Native operators coverage: 100.0% (18/18)
(defaultdict(<class 'int'>, {'Producer': 8, 'Reshape': 2, 'AddAct': 2, 'MaxPooling2D': 2, 'Add': 1, 'PadConv': 2, 'MatMul': 1}), defaultdict(<class 'int'>, {}))
===============
Compile
===============
OK
===============
Create Scheduler
===============
OK
===============
Name nodes
===============
Parameter6 (Producer)
Pooling160_Output_0_reshape0_shape (Producer)
_PadConv_0_weights (Producer)
Parameter88 (Producer)
_PadConv_1_weights (Producer)
Parameter193 (Producer)
Parameter193_reshape1_shape (Producer)
Parameter194 (Producer)
_PadConv_0 (PadConv)
_Reshape_0 (Reshape)
_AddAct_0 (AddAct)
_MaxPooling2D_0 (MaxPooling2D)
_PadConv_1 (PadConv)
_AddAct_1 (AddAct)
_MaxPooling2D_1 (MaxPooling2D)
_Reshape_1 (Reshape)
_MatMul_0 (MatMul)
_Add_0 (Add)
===============
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
===============
0%| | exported 0/28 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/28 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/28 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/28 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/28 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/28 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/28 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
21%|██▏ | exported 6/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 52.31/s]
21%|██▏ | exported 6/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 52.31/s]
21%|██▏ | exported 6/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 52.31/s]
21%|██▏ | exported 6/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 52.31/s]
21%|██▏ | exported 6/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 52.31/s]
21%|██▏ | exported 6/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 52.31/s]
21%|██▏ | exported 6/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 52.31/s]
43%|████▎ | exported 12/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 49.01/s]
43%|████▎ | exported 12/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 49.01/s]
43%|████▎ | exported 12/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 49.01/s]
43%|████▎ | exported 12/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 49.01/s]
43%|████▎ | exported 12/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 49.01/s]
43%|████▎ | exported 12/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 49.01/s]
61%|██████ | exported 17/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.50/s]
61%|██████ | exported 17/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.50/s]
61%|██████ | exported 17/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.50/s]
61%|██████ | exported 17/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.50/s]
61%|██████ | exported 17/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.50/s]
61%|██████ | exported 17/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.50/s]
79%|███████▊ | exported 22/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 44.79/s]
79%|███████▊ | exported 22/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 44.79/s]
79%|███████▊ | exported 22/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 44.79/s]
79%|███████▊ | exported 22/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 44.79/s]
79%|███████▊ | exported 22/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 44.79/s]
79%|███████▊ | exported 22/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 44.79/s]
96%|█████████▋| exported 27/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.20/s]
96%|█████████▋| exported 27/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.20/s]
100%|██████████| exported 28/28 nodes [elapsed: 00:00, remaining: 00:00, rate: 45.88/s]
Processing node: Parameter6[Producer], with backend: export_cpp]
Processing node: Pooling160_Output_0_reshape0_shape[Producer], with backend: export_cpp]
Processing node: _PadConv_0_weights[Producer], with backend: export_cpp]
Processing node: Parameter88[Producer], with backend: export_cpp]
Processing node: _PadConv_1_weights[Producer], with backend: export_cpp]
Processing node: Parameter193[Producer], with backend: export_cpp]
Processing node: Parameter193_reshape1_shape[Producer], with backend: export_cpp]
Processing node: Parameter194[Producer], with backend: export_cpp]
Processing node: _PadConv_1__2[Transpose], with backend: export_cpp]
Processing node: _Reshape_0[Reshape], with backend: export_cpp]
Processing node: _PadConv_0__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_0__3[Transpose], with backend: export_cpp]
Processing node: _PadConv_0[PadConv], with backend: export_cpp]
Processing node: _PadConv_0__1[Transpose], with backend: export_cpp]
Processing node: _AddAct_0[AddAct], with backend: export_cpp]
Processing node: _MaxPooling2D_0__1[Transpose], with backend: export_cpp]
Processing node: _MaxPooling2D_0[MaxPooling2D], with backend: export_cpp]
Processing node: _MaxPooling2D_0__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_1__1[Transpose], with backend: export_cpp]
Processing node: _PadConv_1[PadConv], with backend: export_cpp]
Processing node: _PadConv_1__3[Transpose], with backend: export_cpp]
Processing node: _AddAct_1[AddAct], with backend: export_cpp]
Processing node: _MaxPooling2D_1__1[Transpose], with backend: export_cpp]
Processing node: _MaxPooling2D_1[MaxPooling2D], with backend: export_cpp]
Processing node: _MaxPooling2D_1__2[Transpose], with backend: export_cpp]
Processing node: _Reshape_1[Reshape], with backend: export_cpp]
Processing node: _MatMul_0[MatMul], with backend: export_cpp]
Processing node: _Add_0[Add], with backend: export_cpp]
===============
Generate Random input data
===============
===============
Generate main.cpp
===============
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[33mWARNING[0m] - Reshape_Op: unable to forwardDims() because output dims are data dependent on input#1
[[33mWARNING[0m] - Unable to forward dimensions (circular dependency and/or wrong dimensions and/or data
[[33mWARNING[0m] dependent dimension?). Unable to compute output dims for nodes ["Times212_reshape0
[[33mWARNING[0m] (Reshape)", "Plus214 (Add)", "Times212_reshape1 (Reshape)"].
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[94mNOTICE[0m] - Reshape_Op: ignoring non-empty Shape attribute because input#1 takes precedence
[[94mNOTICE[0m] - Generated memory management info at: export_model/stats/memory_info.png
Found data file: _PadConv_0__3_input_0.h
Using data name: _PadConv_0__3_input_0
Updated export_model/main.cpp successfully.
[33mWarning: Permanently added '192.168.2.40' (ED25519) to the list of known hosts.
[0m
[33mWarning: Permanently added '192.168.2.40' (ED25519) to the list of known hosts.
[0merror.log
Report Details
report.json
{
"GFLOPs": null,
"accuracy": null,
"ambiant_temperature": null,
"benchmark_type": "TYPE1",
"date": "2026-04-14T22:48:27.",
"energy_efficiency": null,
"flash_size": null,
"flash_usage": null,
"inference_engine": "aidge",
"inference_latency": {
"latency_per_layers": [],
"max": 4417.882,
"mean": 4382.8028,
"min": 4373.937,
"std": 12.386405428193427,
"troughput": null
},
"load_accelerator": null,
"load_cpu": null,
"model_file_name": "mnist7.onnx",
"model_size": null,
"nb_inference": 20,
"nb_parameters_model": null,
"postprocess_time": {
"max": null,
"mean": null,
"min": null,
"std": null
},
"power_consumption": null,
"preprocess_time": {
"max": null,
"mean": null,
"min": null,
"std": null
},
"ram_peak_usage": null,
"ram_size": null,
"target": "rpi4b",
"target_id": "0000019c716353c48a919c2708c2e96740c0117e3b39e93019ec189e217f7302",
"temperature": null,
"version": 0,
"version_tag": ""
}