Extracting and Profiling Backbones in Complex Networks

NOTE: The Jupyter Notebook below is included in the Chimera SDK and can be run interactively by running the following CLI command:

$ quadric sdk notebook

From the Jupyter Notebook window in your browser, select the notebook named /quadric/sdk-cli/examples/models/mask_rcnn/mask_rcnn_extraction.ipynb.

import torch, torchvision
from onnxruntime import InferenceSession
from tvm.contrib.epu.chimera_job.quantize import quadric_quantize

import tvm.contrib.epu.chimera_job.constants as sdk_constants
from onnxsim import simplify
import onnx
import tvm.contrib.epu.graphutils as gutils
import warnings

warnings.filterwarnings("ignore")
model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)
x = torch.rand(1, 3, 800, 800)
model_name = "mask_rcnn"

torch.onnx.export(
    model,
    x,  # ONNX requires fixed input size
    model_name + ".onnx",
    do_constant_folding=True,
    dynamic_axes={
        "images_tensors": [0, 1, 2, 3],
        "boxes": [0, 1],
        "labels": [0],
        "scores": [0],
        "masks": [0, 1, 2, 3],
    },
    input_names=["input_image"],
    output_names=["bbox_coords", "bbox_labels", "bbox_scores", "bbox_masks"],
    opset_version=sdk_constants.DEFAULT_ONNX_OPSET,
)

print(model)

MaskRCNN(
  (transform): GeneralizedRCNNTransform(
      Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
      Resize(min_size=(800,), max_size=1333, mode='bilinear')
  )
  (backbone): BackboneWithFPN(
    (body): IntermediateLayerGetter(
      (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
      (bn1): FrozenBatchNorm2d(64, eps=0.0)
      (relu): ReLU(inplace=True)
      (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
      (layer1): Sequential(
        (0): Bottleneck(
          (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(64, eps=0.0)
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(64, eps=0.0)
          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(256, eps=0.0)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (1): FrozenBatchNorm2d(256, eps=0.0)
          )
        )
        (1): Bottleneck(
          (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(64, eps=0.0)
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(64, eps=0.0)
          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(256, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (2): Bottleneck(
          (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(64, eps=0.0)
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(64, eps=0.0)
          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(256, eps=0.0)
          (relu): ReLU(inplace=True)
        )
      )
      (layer2): Sequential(
        (0): Bottleneck(
          (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(128, eps=0.0)
          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(128, eps=0.0)
          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(512, eps=0.0)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
            (1): FrozenBatchNorm2d(512, eps=0.0)
          )
        )
        (1): Bottleneck(
          (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(128, eps=0.0)
          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(128, eps=0.0)
          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(512, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (2): Bottleneck(
          (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(128, eps=0.0)
          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(128, eps=0.0)
          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(512, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (3): Bottleneck(
          (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(128, eps=0.0)
          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(128, eps=0.0)
          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(512, eps=0.0)
          (relu): ReLU(inplace=True)
        )
      )
      (layer3): Sequential(
        (0): Bottleneck(
          (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(256, eps=0.0)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(256, eps=0.0)
          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(1024, eps=0.0)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
            (1): FrozenBatchNorm2d(1024, eps=0.0)
          )
        )
        (1): Bottleneck(
          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(256, eps=0.0)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(256, eps=0.0)
          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(1024, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (2): Bottleneck(
          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(256, eps=0.0)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(256, eps=0.0)
          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(1024, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (3): Bottleneck(
          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(256, eps=0.0)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(256, eps=0.0)
          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(1024, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (4): Bottleneck(
          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(256, eps=0.0)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(256, eps=0.0)
          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(1024, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (5): Bottleneck(
          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(256, eps=0.0)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(256, eps=0.0)
          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(1024, eps=0.0)
          (relu): ReLU(inplace=True)
        )
      )
      (layer4): Sequential(
        (0): Bottleneck(
          (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(512, eps=0.0)
          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(512, eps=0.0)
          (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(2048, eps=0.0)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
            (1): FrozenBatchNorm2d(2048, eps=0.0)
          )
        )
        (1): Bottleneck(
          (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(512, eps=0.0)
          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(512, eps=0.0)
          (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(2048, eps=0.0)
          (relu): ReLU(inplace=True)
        )
        (2): Bottleneck(
          (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn1): FrozenBatchNorm2d(512, eps=0.0)
          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): FrozenBatchNorm2d(512, eps=0.0)
          (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn3): FrozenBatchNorm2d(2048, eps=0.0)
          (relu): ReLU(inplace=True)
        )
      )
    )
    (fpn): FeaturePyramidNetwork(
      (inner_blocks): ModuleList(
        (0): Conv2dNormActivation(
          (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
        )
        (1): Conv2dNormActivation(
          (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
        )
        (2): Conv2dNormActivation(
          (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
        )
        (3): Conv2dNormActivation(
          (0): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (layer_blocks): ModuleList(
        (0-3): 4 x Conv2dNormActivation(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        )
      )
      (extra_blocks): LastLevelMaxPool()
    )
  )
  (rpn): RegionProposalNetwork(
    (anchor_generator): AnchorGenerator()
    (head): RPNHead(
      (conv): Sequential(
        (0): Conv2dNormActivation(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (1): ReLU(inplace=True)
        )
      )
      (cls_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
      (bbox_pred): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
    )
  )
  (roi_heads): RoIHeads(
    (box_roi_pool): MultiScaleRoIAlign(featmap_names=['0', '1', '2', '3'], output_size=(7, 7), sampling_ratio=2)
    (box_head): TwoMLPHead(
      (fc6): Linear(in_features=12544, out_features=1024, bias=True)
      (fc7): Linear(in_features=1024, out_features=1024, bias=True)
    )
    (box_predictor): FastRCNNPredictor(
      (cls_score): Linear(in_features=1024, out_features=91, bias=True)
      (bbox_pred): Linear(in_features=1024, out_features=364, bias=True)
    )
    (mask_roi_pool): MultiScaleRoIAlign(featmap_names=['0', '1', '2', '3'], output_size=(14, 14), sampling_ratio=2)
    (mask_head): MaskRCNNHeads(
      (0): Conv2dNormActivation(
        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU(inplace=True)
      )
      (1): Conv2dNormActivation(
        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU(inplace=True)
      )
      (2): Conv2dNormActivation(
        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU(inplace=True)
      )
      (3): Conv2dNormActivation(
        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU(inplace=True)
      )
    )
    (mask_predictor): MaskRCNNPredictor(
      (conv5_mask): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
      (relu): ReLU(inplace=True)
      (mask_fcn_logits): Conv2d(256, 91, kernel_size=(1, 1), stride=(1, 1))
    )
  )
)

## load your predefined ONNX model
model = onnx.load(model_name + ".onnx")

## convert model
model, check = simplify(model)

assert check, "Simplified ONNX model could not be validated"
onnx.save(model, model_name + "_sim" + ".onnx")

util = gutils.CustomOpReplacer(model)
sub_graph, _ = util.extract_subgraph_by_name_matching(["/backbone/.*"])
model_name = model_name + "_backbone"
onnx.save(sub_graph, model_name + ".onnx")

quantize_result = quadric_quantize(
    model_name + ".onnx", 1, None, None, True, asymmetric_activation=True
)

2026-09-22 02:50 - INFO - epu - quantize - Generating synthetic data
2026-09-22 02:50 - INFO - epu - quantize - Optimized model to opset
2026-09-22 02:50 - INFO - epu - quantize - Saved optimized model to mask_rcnn_backbone_float32_opt.onnx
2026-09-22 02:50 - INFO - epu - quantize - Input shapes: [1, 3, 800, 800]. Input names: /transform/Unsqueeze_12_output_0
2026-09-22 02:50 - INFO - epu - quantize - Output shapes: [[1, 256, 200, 200], [1, 256, 100, 100], [1, 256, 50, 50], [1, 256, 25, 25], [1, 256, 13, 13]]. Output names: ['/backbone/fpn/layer_blocks.0/layer_blocks.0.0/Conv_output_0', '/backbone/fpn/layer_blocks.1/layer_blocks.1.0/Conv_output_0', '/backbone/fpn/layer_blocks.2/layer_blocks.2.0/Conv_output_0', '/backbone/fpn/layer_blocks.3/layer_blocks.3.0/Conv_output_0', '/backbone/fpn/extra_blocks/MaxPool_output_0']
2026-09-22 02:50 - DEBUG - epu - quantize - Full exclusion set for quantization: ['Softmax', 'Sigmoid', 'QuadricCustomOp']
2026-09-22 02:50 - DEBUG - epu - quantize - excl_nodes []
2026-09-22 02:50 - INFO - epu - quantize - Quantization started...
WARNING:root:Please use QuantFormat.QDQ for activation type QInt8 and weight type QInt8. Or it will lead to bad performance on x64.
2026-09-22 02:50 - INFO - epu - quantize - Quantization done succesfully!
2026-09-22 02:50 - INFO - epu - quantize - ONNX full precision model size: 102.51 MB
2026-09-22 02:50 - INFO - epu - quantize - ONNX quantized model size: 25.79 MB
2026-09-22 02:50 - INFO - epu - quantize - Saved quantized model to /quadric/sdk-cli/examples/models/mask_rcnn/mask_rcnn_backbone_opt_asym_int8_q.onnx
2026-09-22 02:50 - INFO - epu - quantize - Saved shape inferenced model to /quadric/sdk-cli/examples/models/mask_rcnn/mask_rcnn_backbone_opt_asym_int8_q.onnx
2026-09-22 02:50 - INFO - epu - quantize - Checking for remaining FLOAT/FLOAT16 types.
2026-09-22 02:50 - INFO - epu - quantize - Model still has FLOAT/FLOAT16 types. Creating ranges for floating point tensors using calibration data
2026-09-22 02:51 - INFO - epu - quantize - Saved tensor ranges to /quadric/sdk-cli/examples/models/mask_rcnn/mask_rcnn_backbone_opt_asym_int8_q.onnx.tranges

from tvm.contrib.epu.chimera_job.chimera_job import ChimeraJob
from tvm.contrib.epu.chimera_job.hw_config import HWConfig

hw_config = HWConfig(ocm_size="16MB")
cgc_job = ChimeraJob(
    model_p=quantize_result.qmodel_path,
    hw_config=hw_config,
    trange_file=quantize_result.tranges_path,
)
cgc_job.compile(quiet=True)

cgc_job.run_inference_harness();

2026-09-22 02:56 - INFO - epu - iss_testing - Found tranges for input: <tvm.contrib.epu.interval.Interval object at 0x7749139c4a00>
FILM 20/20: 100%|███████████████████████████████████████████████████| 20/20 [06:06<00:00, 18.34s/it]
2026-09-22 03:02 - INFO - epu - iss_testing - Found tranges for input: <tvm.contrib.epu.interval.Interval object at 0x774a1817f1c0>
2026-09-22 03:02 - INFO - epu - iss_testing - Started Executing Onnxruntime...
2026-09-22 03:02 - INFO - epu - iss_testing - Done 0:00:00.911585

Run Statistics for Mask RCNN Backbone

print(cgc_job)
cgc_job.plot_run_statistics()

╒═════════════════════╤════════════════════════════════════════════════════════════════════════════════════╕
│ Module Name         │ mask_rcnn_backbone_opt_asym_int8_q_QC_U_1d7_16MB_4kB_128GBps_128GBps_16_OFF_x1_x1  │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ ONNX File           │ /quadric/sdk-cli/examples/models/mask_rcnn/mask_rcnn_backbone_opt_asym_int8_q.onnx │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ Product Target      │ QC-U                                                                               │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ Number of Cores     │ 1                                                                                  │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ ISS Clock Frequency │ 1.700                                                                              │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ L2M Size            │ 16MB                                                                               │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ LRM Size            │ 4kB                                                                                │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ External Read BW    │ 128GBps                                                                            │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ External Write BW   │ 128GBps                                                                            │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ MACS per PE         │ 16                                                                                 │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ Max L2M             │ 15.906MB                                                                           │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ Max LRM             │ 3.000kB                                                                            │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ Max Temp Ext Bytes  │ 36.621MB                                                                           │
├─────────────────────┼────────────────────────────────────────────────────────────────────────────────────┤
│ Network GMACs       │ 88.381                                                                             │
╘═════════════════════╧════════════════════════════════════════════════════════════════════════════════════╛

╒════╤════════╤═════════════════════════════════════════════════════════════╤════════════════════╤══════════════════════════╤═══════╕
│    │ Type   │ Name                                                        │ shape              │ type                     │ mse   │
╞════╪════════╪═════════════════════════════════════════════════════════════╪════════════════════╪══════════════════════════╪═══════╡
│  0 │ Input  │ /transform/Unsqueeze_12_output_0                            │ [1, 3, 800, 800]   │ tensor[FixedPoint32<30>] │ n/a   │
├────┼────────┼─────────────────────────────────────────────────────────────┼────────────────────┼──────────────────────────┼───────┤
│  1 │ Output │ /backbone/fpn/layer_blocks.0/layer_blocks.0.0/Conv_output_0 │ [1, 256, 200, 200] │ tensor[FixedPoint32<28>] │ 0.048 │
├────┼────────┼─────────────────────────────────────────────────────────────┼────────────────────┼──────────────────────────┼───────┤
│  2 │ Output │ /backbone/fpn/layer_blocks.1/layer_blocks.1.0/Conv_output_0 │ [1, 256, 100, 100] │ tensor[FixedPoint32<28>] │ 0.019 │
├────┼────────┼─────────────────────────────────────────────────────────────┼────────────────────┼──────────────────────────┼───────┤
│  3 │ Output │ /backbone/fpn/layer_blocks.2/layer_blocks.2.0/Conv_output_0 │ [1, 256, 50, 50]   │ tensor[FixedPoint32<28>] │ 0.023 │
├────┼────────┼─────────────────────────────────────────────────────────────┼────────────────────┼──────────────────────────┼───────┤
│  4 │ Output │ /backbone/fpn/layer_blocks.3/layer_blocks.3.0/Conv_output_0 │ [1, 256, 25, 25]   │ tensor[FixedPoint32<28>] │ 0.022 │
├────┼────────┼─────────────────────────────────────────────────────────────┼────────────────────┼──────────────────────────┼───────┤
│  5 │ Output │ /backbone/fpn/extra_blocks/MaxPool_output_0                 │ [1, 256, 13, 13]   │ tensor[FixedPoint32<28>] │ 0.022 │
╘════╧════════╧═════════════════════════════════════════════════════════════╧════════════════════╧══════════════════════════╧═══════╛

Post-ISS Report 1.7 GHz ***
Fully placed-and-routed gate simulation: 
╒══════════════════════════════════╤═════════╕
│ Latency (ms)                     │ 11.32   │
├──────────────────────────────────┼─────────┤
│ FPS                              │ 88.37   │
├──────────────────────────────────┼─────────┤
│ Average Power @ 3nm SSGNP (mW)   │ 3959.90 │
├──────────────────────────────────┼─────────┤
│ FPS per Watt @ 3nm SSGNP (FPS/W) │ 22.32   │
├──────────────────────────────────┼─────────┤
│ Ext Rd Bytes (MB)                │ 130.50  │
├──────────────────────────────────┼─────────┤
│ Ext Wr Bytes (MB)                │ 139.48  │
├──────────────────────────────────┼─────────┤
│ Avg Ext Rd BW (GBps)             │ 11.26   │
├──────────────────────────────────┼─────────┤
│ Avg Ext Wr BW (GBps)             │ 12.04   │
├──────────────────────────────────┼─────────┤
│ MAC Utilization                  │ 28.04%  │
╘══════════════════════════════════╧═════════╛
*** Data generated using 7nm SSGNP gatesim and scaled to 3nm

[SDK-CLI] : TotalCycles: 19,236,547
[SDK-CLI] : Executions/second: 88.37

compute      : ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 6.055M
data_array   : ▇▇▇▇ 715.203K
mac          : ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 8.681M
data_external: ▇▇▇▇▇▇▇▇▇▇▇ 1.943M
data_ocm     : ▇▇▇▇▇▇▇▇▇ 1.6M

for more information check run directory: /quadric/sdk-cli/examples/models/mask_rcnn/ccl_build/mask_rcnn_backbone_opt_asym_int8_q_QC_U_1d7_16MB_4kB_128GBps_128GBps_16_OFF_x1_x1/run/20260922_025643_a7bff0


2026-09-22 03:02 - INFO - epu - chimera_job - Combined plots generated and saved to: 
/quadric/sdk-cli/examples/models/mask_rcnn/ccl_build/mask_rcnn_backbone_opt_asym_int8_q_QC_U_1d7_16MB_4kB_128GBps_128GBps_16_OFF_x1_x1/run/20260922_025643_a7bff0/data/mask_rcnn_backbone_opt_asym_int8_q_QC_U_1d7_16MB_4kB_128GBps_128GBps_16_OFF_x1_x1.combined.png





'/quadric/sdk-cli/examples/models/mask_rcnn/ccl_build/mask_rcnn_backbone_opt_asym_int8_q_QC_U_1d7_16MB_4kB_128GBps_128GBps_16_OFF_x1_x1/run/20260922_025643_a7bff0/data'