124076 - rpi5 aidge
124076 - rpi5 aidge
Summary: Pipeline succeeded and valid report was generated.
Model Details
- model name : tinyyolov2-8.onnx
- model url : Download here
Logs Details
user.log
MODEL : tinyyolov28.onnx
===============
ONNX Graph
===============
Number of input = 45 is not supported (max 1)
image ['None', 3, 416, 416]
===============
Aidge Graph
===============
Node(name='pooling5', optype='PaddedMaxPooling2D', parents: [1, 0, 0, 0], children: [[1], []])
Node(name='BatchNormalization_mean6', optype='Producer', children: [[1]])
Node(name='BatchNormalization_scale7', optype='Producer', children: [[1]])
Node(name='convolution5', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='convolution6_W', optype='Producer', children: [[1]])
Node(name='activation4', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='pooling3', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='convolution5_W', optype='Producer', children: [[1]])
Node(name='BatchNormalization_scale5', optype='Producer', children: [[1]])
Node(name='BatchNormalization_variance6', optype='Producer', children: [[1]])
Node(name='batchnorm7', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='BatchNormalization_B', optype='Producer', children: [[1]])
Node(name='BatchNormalization_variance4', optype='Producer', children: [[1]])
Node(name='pooling2', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='BatchNormalization_scale4', optype='Producer', children: [[1]])
Node(name='BatchNormalization_mean4', optype='Producer', children: [[1]])
Node(name='activation2', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='BatchNormalization_mean2', optype='Producer', children: [[1]])
Node(name='BatchNormalization_B4', optype='Producer', children: [[1]])
Node(name='convolution2', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='activation1', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='BatchNormalization_variance2', optype='Producer', children: [[1]])
Node(name='convolution7_W', optype='Producer', children: [[1]])
Node(name='BatchNormalization_variance5', optype='Producer', children: [[1]])
Node(name='convolution1', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='BatchNormalization_mean7', optype='Producer', children: [[1]])
Node(name='convolution_W', optype='Producer', children: [[1]])
Node(name='BatchNormalization_mean', optype='Producer', children: [[1]])
Node(name='convolution1_W', optype='Producer', children: [[1]])
Node(name='BatchNormalization_scale', optype='Producer', children: [[1]])
Node(name='activation', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='batchnorm', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='scalerPreprocessor_scale', optype='Producer', children: [[1]])
Node(name='batchnorm1', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='batchnorm2', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='Add', optype='Add', parents: [1, 1], children: [[1]])
Node(name='scalerPreprocessor_bias', optype='Producer', children: [[1]])
Node(name='BatchNormalization_variance', optype='Producer', children: [[1]])
Node(name='BatchNormalization_scale3', optype='Producer', children: [[1]])
Node(name='convolution2_W', optype='Producer', children: [[1]])
Node(name='BatchNormalization_variance1', optype='Producer', children: [[1]])
Node(name='convolution', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='BatchNormalization_mean1', optype='Producer', children: [[1]])
Node(name='BatchNormalization_variance3', optype='Producer', children: [[1]])
Node(name='BatchNormalization_B1', optype='Producer', children: [[1]])
Node(name='BatchNormalization_scale1', optype='Producer', children: [[1]])
Node(name='BatchNormalization_B3', optype='Producer', children: [[1]])
Node(name='convolution8', optype='Conv2D', parents: [1, 1, 1], children: [[]])
Node(name='activation7', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='convolution7', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='BatchNormalization_mean5', optype='Producer', children: [[1]])
Node(name='activation6', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='BatchNormalization_mean3', optype='Producer', children: [[1]])
Node(name='BatchNormalization_scale6', optype='Producer', children: [[1]])
Node(name='convolution6', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='activation5', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='pooling4', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='convolution8_B', optype='Producer', children: [[1]])
Node(name='convolution4', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='BatchNormalization_scale2', optype='Producer', children: [[1]])
Node(name='activation3', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='convolution3', optype='PaddedConv2D', parents: [1, 1, 0, 0, 0, 0], children: [[1]])
Node(name='batchnorm5', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='batchnorm6', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='pooling1', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='BatchNormalization_variance7', optype='Producer', children: [[1]])
Node(name='batchnorm4', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='pooling', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='batchnorm3', optype='BatchNorm2D', parents: [1, 1, 1, 1, 1], children: [[1]])
Node(name='Mul', optype='Mul', parents: [0, 1], children: [[1]])
Node(name='convolution8_W', optype='Producer', children: [[1]])
Node(name='convolution4_W', optype='Producer', children: [[1]])
Node(name='BatchNormalization_B7', optype='Producer', children: [[1]])
Node(name='convolution3_W', optype='Producer', children: [[1]])
Node(name='BatchNormalization_B6', optype='Producer', children: [[1]])
Node(name='BatchNormalization_B2', optype='Producer', children: [[1]])
Node(name='BatchNormalization_B5', optype='Producer', children: [[1]])
===============
Supported nodes
===============
Native operators: 77 (9 types)
- Add: 1
- BatchNorm2D: 8
- Conv2D: 1
- LeakyReLU: 8
- MaxPooling2D: 5
- Mul: 1
- PaddedConv2D: 8
- PaddedMaxPooling2D: 1
- Producer: 44
Generic operators: 0 (0 types)
Native types coverage: 100.0% (9/9)
Native operators coverage: 100.0% (77/77)
(defaultdict(<class 'int'>, {'Producer': 44, 'BatchNorm2D': 8, 'Add': 1, 'Conv2D': 1, 'LeakyReLU': 8, 'PaddedConv2D': 8, 'PaddedMaxPooling2D': 1, 'MaxPooling2D': 5, 'Mul': 1}), defaultdict(<class 'int'>, {}))
===============\Graph manipulation
===============
Remove flatten
Fuse batchnorm
Expand metaop
Fuse to metaop
===============
New Aidge Graph
===============
Node(name='convolution6_W', optype='Producer', children: [[1]])
Node(name='convolution7_b', optype='Producer', children: [[1]])
Node(name='pooling4', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='Add', optype='Add', parents: [1, 1], children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='', optype='PadMaxPool', parents: [1, 0, 0, 0], children: [[1], []])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='scalerPreprocessor_bias', optype='Producer', children: [[1]])
Node(name='convolution8_W', optype='Producer', children: [[1]])
Node(name='activation5', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='convolution2_b', optype='Producer', children: [[1]])
Node(name='convolution_b', optype='Producer', children: [[1]])
Node(name='convolution8', optype='Conv2D', parents: [1, 1, 1], children: [[]])
Node(name='convolution1_W', optype='Producer', children: [[1]])
Node(name='activation6', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='activation7', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='activation1', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='pooling1', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='activation2', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='convolution5_W', optype='Producer', children: [[1]])
Node(name='convolution1_b', optype='Producer', children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='convolution4_W', optype='Producer', children: [[1]])
Node(name='pooling', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='activation4', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='convolution4_b', optype='Producer', children: [[1]])
Node(name='scalerPreprocessor_scale', optype='Producer', children: [[1]])
Node(name='convolution2_W', optype='Producer', children: [[1]])
Node(name='convolution6_b', optype='Producer', children: [[1]])
Node(name='convolution5_b', optype='Producer', children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='Mul', optype='Mul', parents: [0, 1], children: [[1]])
Node(name='convolution8_B', optype='Producer', children: [[1]])
Node(name='convolution3_W', optype='Producer', children: [[1]])
Node(name='activation', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='convolution7_W', optype='Producer', children: [[1]])
Node(name='convolution_W', optype='Producer', children: [[1]])
Node(name='convolution3_b', optype='Producer', children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='', optype='PadConv', parents: [1, 1, 1, 0, 0, 0], children: [[1]])
Node(name='activation3', optype='LeakyReLU', parents: [1], children: [[1]])
Node(name='pooling3', optype='MaxPooling2D', parents: [1], children: [[1], []])
Node(name='pooling2', optype='MaxPooling2D', parents: [1], children: [[1], []])
===============
Supported nodes 2
===============
Native operators: 45 (8 types)
- Add: 1
- Conv2D: 1
- LeakyReLU: 8
- MaxPooling2D: 5
- Mul: 1
- PadConv: 8
- PadMaxPool: 1
- Producer: 20
Generic operators: 0 (0 types)
Native types coverage: 100.0% (8/8)
Native operators coverage: 100.0% (45/45)
(defaultdict(<class 'int'>, {'MaxPooling2D': 5, 'LeakyReLU': 8, 'Producer': 20, 'PadConv': 8, 'Add': 1, 'Mul': 1, 'PadMaxPool': 1, 'Conv2D': 1}), defaultdict(<class 'int'>, {}))
===============
Supported nodes
===============
Native operators: 45 (8 types)
- Add: 1
- Conv2D: 1
- LeakyReLU: 8
- MaxPooling2D: 5
- Mul: 1
- PadConv: 8
- PadMaxPool: 1
- Producer: 20
Generic operators: 0 (0 types)
Native types coverage: 100.0% (8/8)
Native operators coverage: 100.0% (45/45)
(defaultdict(<class 'int'>, {'LeakyReLU': 8, 'PadConv': 8, 'MaxPooling2D': 5, 'Mul': 1, 'Producer': 20, 'Add': 1, 'Conv2D': 1, 'PadMaxPool': 1}), defaultdict(<class 'int'>, {}))
===============
Compile
===============
OK
===============
Create Scheduler
===============
OK
===============
Name nodes
===============
_PadConv_3_biases (Producer)
_PadConv_3_weights (Producer)
_PadConv_2_weights (Producer)
_PadConv_4_biases (Producer)
_PadConv_4_weights (Producer)
_PadConv_5_biases (Producer)
_PadConv_5_weights (Producer)
_PadConv_6_biases (Producer)
_PadConv_6_weights (Producer)
_PadConv_7_biases (Producer)
_PadConv_7_weights (Producer)
_Conv2D_0_weights (Producer)
_Conv2D_0_biases (Producer)
_PadConv_0_biases (Producer)
_PadConv_2_biases (Producer)
scalerPreprocessor_bias (Producer)
scalerPreprocessor_scale (Producer)
_PadConv_1_biases (Producer)
_PadConv_1_weights (Producer)
_PadConv_0_weights (Producer)
_Mul_0 (Mul)
_Add_0 (Add)
_PadConv_0 (PadConv)
_LeakyReLU_0 (LeakyReLU)
_MaxPooling2D_0 (MaxPooling2D)
_PadConv_1 (PadConv)
_LeakyReLU_1 (LeakyReLU)
_MaxPooling2D_1 (MaxPooling2D)
_PadConv_2 (PadConv)
_LeakyReLU_2 (LeakyReLU)
_MaxPooling2D_2 (MaxPooling2D)
_PadConv_3 (PadConv)
_LeakyReLU_3 (LeakyReLU)
_MaxPooling2D_3 (MaxPooling2D)
_PadConv_4 (PadConv)
_LeakyReLU_4 (LeakyReLU)
_MaxPooling2D_4 (MaxPooling2D)
_PadConv_5 (PadConv)
_LeakyReLU_5 (LeakyReLU)
_PadMaxPool_0 (PadMaxPool)
_PadConv_6 (PadConv)
_LeakyReLU_6 (LeakyReLU)
_PadConv_7 (PadConv)
_LeakyReLU_7 (LeakyReLU)
_Conv2D_0 (Conv2D)
===============
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 0/84 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/84 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
0%| | exported 0/84 nodes [elapsed: 00:00, remaining: ?, rate: ?/s]
2%|▏ | exported 2/84 nodes [elapsed: 00:00, remaining: 00:09, rate: 8.54/s]
2%|▏ | exported 2/84 nodes [elapsed: 00:00, remaining: 00:09, rate: 8.54/s]
2%|▏ | exported 2/84 nodes [elapsed: 00:00, remaining: 00:09, rate: 8.54/s]
2%|▏ | exported 2/84 nodes [elapsed: 00:00, remaining: 00:09, rate: 8.54/s]
6%|▌ | exported 5/84 nodes [elapsed: 00:01, remaining: 00:19, rate: 3.99/s]
6%|▌ | exported 5/84 nodes [elapsed: 00:01, remaining: 00:19, rate: 3.99/s]
6%|▌ | exported 5/84 nodes [elapsed: 00:01, remaining: 00:19, rate: 3.99/s]
8%|▊ | exported 7/84 nodes [elapsed: 00:04, remaining: 01:02, rate: 1.23/s]
8%|▊ | exported 7/84 nodes [elapsed: 00:04, remaining: 01:02, rate: 1.23/s]
8%|▊ | exported 7/84 nodes [elapsed: 00:04, remaining: 01:02, rate: 1.23/s]
11%|█ | exported 9/84 nodes [elapsed: 00:17, remaining: 03:40, rate: 2.94s/]
11%|█ | exported 9/84 nodes [elapsed: 00:17, remaining: 03:40, rate: 2.94s/]
11%|█ | exported 9/84 nodes [elapsed: 00:17, remaining: 03:40, rate: 2.94s/]
13%|█▎ | exported 11/84 nodes [elapsed: 00:44, remaining: 07:56, rate: 6.53s/]
13%|█▎ | exported 11/84 nodes [elapsed: 00:44, remaining: 07:56, rate: 6.53s/]
14%|█▍ | exported 12/84 nodes [elapsed: 00:45, remaining: 06:27, rate: 5.38s/]
14%|█▍ | exported 12/84 nodes [elapsed: 00:45, remaining: 06:27, rate: 5.38s/]
14%|█▍ | exported 12/84 nodes [elapsed: 00:45, remaining: 06:27, rate: 5.38s/]
14%|█▍ | exported 12/84 nodes [elapsed: 00:45, remaining: 06:27, rate: 5.38s/]
14%|█▍ | exported 12/84 nodes [elapsed: 00:45, remaining: 06:27, rate: 5.38s/]
14%|█▍ | exported 12/84 nodes [elapsed: 00:45, remaining: 06:27, rate: 5.38s/]
14%|█▍ | exported 12/84 nodes [elapsed: 00:45, remaining: 06:27, rate: 5.38s/]
21%|██▏ | exported 18/84 nodes [elapsed: 00:45, remaining: 02:13, rate: 2.02s/]
21%|██▏ | exported 18/84 nodes [elapsed: 00:45, remaining: 02:13, rate: 2.02s/]
21%|██▏ | exported 18/84 nodes [elapsed: 00:45, remaining: 02:13, rate: 2.02s/]
21%|██▏ | exported 18/84 nodes [elapsed: 00:45, remaining: 02:13, rate: 2.02s/]
21%|██▏ | exported 18/84 nodes [elapsed: 00:45, remaining: 02:13, rate: 2.02s/]
21%|██▏ | exported 18/84 nodes [elapsed: 00:45, remaining: 02:13, rate: 2.02s/]
27%|██▋ | exported 23/84 nodes [elapsed: 00:45, remaining: 01:11, rate: 1.17s/]
27%|██▋ | exported 23/84 nodes [elapsed: 00:45, remaining: 01:11, rate: 1.17s/]
27%|██▋ | exported 23/84 nodes [elapsed: 00:45, remaining: 01:11, rate: 1.17s/]
27%|██▋ | exported 23/84 nodes [elapsed: 00:45, remaining: 01:11, rate: 1.17s/]
27%|██▋ | exported 23/84 nodes [elapsed: 00:45, remaining: 01:11, rate: 1.17s/]
27%|██▋ | exported 23/84 nodes [elapsed: 00:45, remaining: 01:11, rate: 1.17s/]
33%|███▎ | exported 28/84 nodes [elapsed: 00:45, remaining: 00:41, rate: 1.36/s]
33%|███▎ | exported 28/84 nodes [elapsed: 00:45, remaining: 00:41, rate: 1.36/s]
33%|███▎ | exported 28/84 nodes [elapsed: 00:45, remaining: 00:41, rate: 1.36/s]
33%|███▎ | exported 28/84 nodes [elapsed: 00:45, remaining: 00:41, rate: 1.36/s]
33%|███▎ | exported 28/84 nodes [elapsed: 00:46, remaining: 00:41, rate: 1.36/s]
33%|███▎ | exported 28/84 nodes [elapsed: 00:46, remaining: 00:41, rate: 1.36/s]
39%|███▉ | exported 33/84 nodes [elapsed: 00:46, remaining: 00:24, rate: 2.06/s]
39%|███▉ | exported 33/84 nodes [elapsed: 00:46, remaining: 00:24, rate: 2.06/s]
39%|███▉ | exported 33/84 nodes [elapsed: 00:46, remaining: 00:24, rate: 2.06/s]
39%|███▉ | exported 33/84 nodes [elapsed: 00:46, remaining: 00:24, rate: 2.06/s]
39%|███▉ | exported 33/84 nodes [elapsed: 00:46, remaining: 00:24, rate: 2.06/s]
39%|███▉ | exported 33/84 nodes [elapsed: 00:46, remaining: 00:24, rate: 2.06/s]
45%|████▌ | exported 38/84 nodes [elapsed: 00:46, remaining: 00:15, rate: 3.03/s]
45%|████▌ | exported 38/84 nodes [elapsed: 00:46, remaining: 00:15, rate: 3.03/s]
45%|████▌ | exported 38/84 nodes [elapsed: 00:46, remaining: 00:15, rate: 3.03/s]
45%|████▌ | exported 38/84 nodes [elapsed: 00:46, remaining: 00:15, rate: 3.03/s]
45%|████▌ | exported 38/84 nodes [elapsed: 00:46, remaining: 00:15, rate: 3.03/s]
45%|████▌ | exported 38/84 nodes [elapsed: 00:46, remaining: 00:15, rate: 3.03/s]
51%|█████ | exported 43/84 nodes [elapsed: 00:46, remaining: 00:09, rate: 4.33/s]
51%|█████ | exported 43/84 nodes [elapsed: 00:46, remaining: 00:09, rate: 4.33/s]
51%|█████ | exported 43/84 nodes [elapsed: 00:46, remaining: 00:09, rate: 4.33/s]
51%|█████ | exported 43/84 nodes [elapsed: 00:46, remaining: 00:09, rate: 4.33/s]
51%|█████ | exported 43/84 nodes [elapsed: 00:46, remaining: 00:09, rate: 4.33/s]
51%|█████ | exported 43/84 nodes [elapsed: 00:46, remaining: 00:09, rate: 4.33/s]
57%|█████▋ | exported 48/84 nodes [elapsed: 00:46, remaining: 00:05, rate: 6.03/s]
57%|█████▋ | exported 48/84 nodes [elapsed: 00:46, remaining: 00:05, rate: 6.03/s]
57%|█████▋ | exported 48/84 nodes [elapsed: 00:46, remaining: 00:05, rate: 6.03/s]
57%|█████▋ | exported 48/84 nodes [elapsed: 00:46, remaining: 00:05, rate: 6.03/s]
57%|█████▋ | exported 48/84 nodes [elapsed: 00:46, remaining: 00:05, rate: 6.03/s]
57%|█████▋ | exported 48/84 nodes [elapsed: 00:46, remaining: 00:05, rate: 6.03/s]
63%|██████▎ | exported 53/84 nodes [elapsed: 00:46, remaining: 00:03, rate: 8.24/s]
63%|██████▎ | exported 53/84 nodes [elapsed: 00:46, remaining: 00:03, rate: 8.24/s]
63%|██████▎ | exported 53/84 nodes [elapsed: 00:46, remaining: 00:03, rate: 8.24/s]
63%|██████▎ | exported 53/84 nodes [elapsed: 00:46, remaining: 00:03, rate: 8.24/s]
63%|██████▎ | exported 53/84 nodes [elapsed: 00:46, remaining: 00:03, rate: 8.24/s]
63%|██████▎ | exported 53/84 nodes [elapsed: 00:46, remaining: 00:03, rate: 8.24/s]
69%|██████▉ | exported 58/84 nodes [elapsed: 00:46, remaining: 00:02, rate: 10.95/s]
69%|██████▉ | exported 58/84 nodes [elapsed: 00:46, remaining: 00:02, rate: 10.95/s]
69%|██████▉ | exported 58/84 nodes [elapsed: 00:46, remaining: 00:02, rate: 10.95/s]
69%|██████▉ | exported 58/84 nodes [elapsed: 00:46, remaining: 00:02, rate: 10.95/s]
69%|██████▉ | exported 58/84 nodes [elapsed: 00:46, remaining: 00:02, rate: 10.95/s]
69%|██████▉ | exported 58/84 nodes [elapsed: 00:46, remaining: 00:02, rate: 10.95/s]
75%|███████▌ | exported 63/84 nodes [elapsed: 00:46, remaining: 00:01, rate: 14.19/s]
75%|███████▌ | exported 63/84 nodes [elapsed: 00:46, remaining: 00:01, rate: 14.19/s]
75%|███████▌ | exported 63/84 nodes [elapsed: 00:46, remaining: 00:01, rate: 14.19/s]
75%|███████▌ | exported 63/84 nodes [elapsed: 00:46, remaining: 00:01, rate: 14.19/s]
75%|███████▌ | exported 63/84 nodes [elapsed: 00:46, remaining: 00:01, rate: 14.19/s]
75%|███████▌ | exported 63/84 nodes [elapsed: 00:46, remaining: 00:01, rate: 14.19/s]
81%|████████ | exported 68/84 nodes [elapsed: 00:46, remaining: 00:00, rate: 17.75/s]
81%|████████ | exported 68/84 nodes [elapsed: 00:46, remaining: 00:00, rate: 17.75/s]
81%|████████ | exported 68/84 nodes [elapsed: 00:46, remaining: 00:00, rate: 17.75/s]
81%|████████ | exported 68/84 nodes [elapsed: 00:46, remaining: 00:00, rate: 17.75/s]
81%|████████ | exported 68/84 nodes [elapsed: 00:46, remaining: 00:00, rate: 17.75/s]
81%|████████ | exported 68/84 nodes [elapsed: 00:46, remaining: 00:00, rate: 17.75/s]
87%|████████▋ | exported 73/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 21.73/s]
87%|████████▋ | exported 73/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 21.73/s]
87%|████████▋ | exported 73/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 21.73/s]
87%|████████▋ | exported 73/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 21.73/s]
87%|████████▋ | exported 73/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 21.73/s]
87%|████████▋ | exported 73/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 21.73/s]
93%|█████████▎| exported 78/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 25.52/s]
93%|█████████▎| exported 78/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 25.52/s]
93%|█████████▎| exported 78/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 25.52/s]
93%|█████████▎| exported 78/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 25.52/s]
93%|█████████▎| exported 78/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 25.52/s]
93%|█████████▎| exported 78/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 25.52/s]
99%|█████████▉| exported 83/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 28.75/s]
99%|█████████▉| exported 83/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 28.75/s]
100%|██████████| exported 84/84 nodes [elapsed: 00:47, remaining: 00:00, rate: 1.78/s]
Processing node: _PadConv_3_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_3_weights[Producer], with backend: export_cpp]
Processing node: _PadConv_2_weights[Producer], with backend: export_cpp]
Processing node: _PadConv_4_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_4_weights[Producer], with backend: export_cpp]
Processing node: _PadConv_5_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_5_weights[Producer], with backend: export_cpp]
Processing node: _PadConv_6_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_6_weights[Producer], with backend: export_cpp]
Processing node: _PadConv_7_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_7_weights[Producer], with backend: export_cpp]
Processing node: _Conv2D_0_weights[Producer], with backend: export_cpp]
Processing node: _Conv2D_0_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_0_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_2_biases[Producer], with backend: export_cpp]
Processing node: scalerPreprocessor_bias[Producer], with backend: export_cpp]
Processing node: scalerPreprocessor_scale[Producer], with backend: export_cpp]
Processing node: _PadConv_1_biases[Producer], with backend: export_cpp]
Processing node: _PadConv_1_weights[Producer], with backend: export_cpp]
Processing node: _PadConv_0_weights[Producer], with backend: export_cpp]
Processing node: _PadConv_6__1[Transpose], with backend: export_cpp]
Processing node: _PadConv_0__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_5__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_7__1[Transpose], with backend: export_cpp]
Processing node: _PadConv_4_[Transpose], with backend: export_cpp]
Processing node: _Mul_0[Mul], with backend: export_cpp]
Processing node: _PadConv_2__1[Transpose], with backend: export_cpp]
Processing node: _PadConv_3__3[Transpose], with backend: export_cpp]
Processing node: _Conv2D_0__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_1__2[Transpose], with backend: export_cpp]
Processing node: _Add_0[Add], with backend: export_cpp]
Processing node: _PadConv_0__1[Transpose], with backend: export_cpp]
Processing node: _PadConv_0[PadConv], with backend: export_cpp]
Processing node: _PadConv_0__3[Transpose], with backend: export_cpp]
Processing node: _LeakyReLU_0[LeakyReLU], 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: _LeakyReLU_1[LeakyReLU], 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: _PadConv_2_[Transpose], with backend: export_cpp]
Processing node: _PadConv_2[PadConv], with backend: export_cpp]
Processing node: _PadConv_2__3[Transpose], with backend: export_cpp]
Processing node: _LeakyReLU_2[LeakyReLU], with backend: export_cpp]
Processing node: _MaxPooling2D_2__1[Transpose], with backend: export_cpp]
Processing node: _MaxPooling2D_2[MaxPooling2D], with backend: export_cpp]
Processing node: _MaxPooling2D_2__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_3_[Transpose], with backend: export_cpp]
Processing node: _PadConv_3[PadConv], with backend: export_cpp]
Processing node: _PadConv_3__1[Transpose], with backend: export_cpp]
Processing node: _LeakyReLU_3[LeakyReLU], with backend: export_cpp]
Processing node: _MaxPooling2D_3__1[Transpose], with backend: export_cpp]
Processing node: _MaxPooling2D_3[MaxPooling2D], with backend: export_cpp]
Processing node: _MaxPooling2D_3__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_4__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_4[PadConv], with backend: export_cpp]
Processing node: _PadConv_4__3[Transpose], with backend: export_cpp]
Processing node: _LeakyReLU_4[LeakyReLU], with backend: export_cpp]
Processing node: _MaxPooling2D_4__1[Transpose], with backend: export_cpp]
Processing node: _MaxPooling2D_4[MaxPooling2D], with backend: export_cpp]
Processing node: _MaxPooling2D_4__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_5_[Transpose], with backend: export_cpp]
Processing node: _PadConv_5[PadConv], with backend: export_cpp]
Processing node: _PadConv_5__1[Transpose], with backend: export_cpp]
Processing node: _LeakyReLU_5[LeakyReLU], with backend: export_cpp]
Processing node: _PadMaxPool_0__1[Transpose], with backend: export_cpp]
Processing node: _PadMaxPool_0[PadMaxPool], with backend: export_cpp]
Processing node: _PadMaxPool_0__2[Transpose], with backend: export_cpp]
Processing node: _PadConv_6__3[Transpose], with backend: export_cpp]
Processing node: _PadConv_6[PadConv], with backend: export_cpp]
Processing node: _PadConv_6_[Transpose], with backend: export_cpp]
Processing node: _LeakyReLU_6[LeakyReLU], with backend: export_cpp]
Processing node: _PadConv_7_[Transpose], with backend: export_cpp]
Processing node: _PadConv_7[PadConv], with backend: export_cpp]
Processing node: _PadConv_7__2[Transpose], with backend: export_cpp]
Processing node: _LeakyReLU_7[LeakyReLU], with backend: export_cpp]
Processing node: _Conv2D_0__1[Transpose], with backend: export_cpp]
Processing node: _Conv2D_0[Conv2D], with backend: export_cpp]
Processing node: _Conv2D_0__3[Transpose], with backend: export_cpp]
===============
Generate Random input data
===============
===============
Generate main.cpp
===============
[[94mNOTICE[0m] - Generated memory management info at: export_model/stats/memory_info.png
Found data file: _Mul_0_input_0.h
Using data name: _Mul_0_input_0
Updated export_model/main.cpp successfully.
[33mWarning: Permanently added '192.168.2.10' (ED25519) to the list of known hosts.
[0m
[33mWarning: Permanently added '192.168.2.10' (ED25519) to the list of known hosts.
[0merror.log
Report Details
report.json
{
"GFLOPs": null,
"accuracy": null,
"ambiant_temperature": null,
"benchmark_type": "TYPE1",
"date": "2026-04-14T22:45:51.",
"energy_efficiency": null,
"flash_size": null,
"flash_usage": null,
"inference_engine": "aidge",
"inference_latency": {
"latency_per_layers": [],
"max": 1153359.32,
"mean": 1148670.1903000001,
"min": 1144477.7140000002,
"std": 2346.289055859971,
"troughput": null
},
"load_accelerator": null,
"load_cpu": null,
"model_file_name": "tinyyolov28.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": "rpi5",
"target_id": "0000019c71638acf37948e8933e2246c7ee24eb06307d06986d991b6e014d767",
"temperature": null,
"version": 0,
"version_tag": ""
}