python -m monai.bundle run system --config_file ./projects/cifar10/experiments/monai_bundle_prototype.yaml 2024-02-07 18:17:52,778 - INFO - --- input summary of monai.bundle.scripts.run --- 2024-02-07 18:17:52,778 - INFO - > config_file: './projects/cifar10/experiments/monai_bundle_prototype.yaml' 2024-02-07 18:17:52,778 - INFO - > run_id: 'system' 2024-02-07 18:17:52,778 - INFO - --- /home/suraj/.local/lib/python3.8/site-packages/monai/utils/deprecate_utils.py:321: FutureWarning: monai.bundle.workflows ConfigWorkflow.__init__:workflow_type: Current default value of argument `workflow_type=None` has been deprecated since version 1.2. It will be changed to `workflow_type=train` in version 1.4. warn_deprecated(argname, msg, warning_category) 2024-02-07 18:17:52,779 - WARNING - Default logging file in projects/cifar10/experiments/logging.conf does not exist, skipping logging. 2024-02-07 18:17:52,789 - ERROR - Cannot find the metadata config file: projects/cifar10/experiments/metadata.json. Please see: https://docs.monai.io/en/stable/mb_specification.html Files already downloaded and verified Files already downloaded and verified Files already downloaded and verified Files already downloaded and verified ╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮ │ /home/suraj/.local/lib/python3.8/site-packages/monai/utils/module.py:261 in instantiate │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ TypeError: __init__() got an unexpected keyword argument 'test' The above exception was the direct cause of the following exception: ╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/config_item.py:293 in instantiate │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/utils/module.py:271 in instantiate │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ RuntimeError: Failed to instantiate component 'lighter.LighterSystem' with kwargs: {'batch_size': 512, 'pin_memory': True, 'num_workers': 6, 'test': 5, 'model': EfficientNetBN( (_conv_stem): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), bias=False) (_conv_stem_padding): ConstantPad2d(padding=(0, 1, 0, 1), value=0.0) (_bn0): BatchNorm2d(32, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_blocks): Sequential( (0): Sequential( (0): MBConvBlock( (_expand_conv): Identity() (_expand_conv_padding): Identity() (_bn0): Identity() (_depthwise_conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), groups=32, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(32, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(32, 8, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(8, 32, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(16, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (1): Sequential( (1): MBConvBlock( (_expand_conv): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), groups=96, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(0, 1, 0, 1), value=0.0) (_bn1): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(96, 4, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(4, 96, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (2): MBConvBlock( (_expand_conv): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), groups=144, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (2): Sequential( (3): MBConvBlock( (_expand_conv): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(144, 144, kernel_size=(5, 5), stride=(2, 2), groups=144, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 2, 1, 2), value=0.0) (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (4): MBConvBlock( (_expand_conv): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), groups=240, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (3): Sequential( (5): MBConvBlock( (_expand_conv): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(240, 240, kernel_size=(3, 3), stride=(2, 2), groups=240, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(0, 1, 0, 1), value=0.0) (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(240, 80, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (6): MBConvBlock( (_expand_conv): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (7): MBConvBlock( (_expand_conv): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (4): Sequential( (8): MBConvBlock( (_expand_conv): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(480, 480, kernel_size=(5, 5), stride=(1, 1), groups=480, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(480, 112, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (9): MBConvBlock( (_expand_conv): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (10): MBConvBlock( (_expand_conv): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (5): Sequential( (11): MBConvBlock( (_expand_conv): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(672, 672, kernel_size=(5, 5), stride=(2, 2), groups=672, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 2, 1, 2), value=0.0) (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (12): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (13): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (14): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (6): Sequential( (15): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(3, 3), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 320, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(320, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) ) (_conv_head): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False) (_conv_head_padding): Identity() (_bn1): BatchNorm2d(1280, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_avg_pooling): AdaptiveAvgPool2d(output_size=1) (_dropout): Dropout(p=0.2, inplace=False) (_fc): Linear(in_features=1280, out_features=10, bias=True) (_swish): MemoryEfficientSwish() ), 'criterion': CrossEntropyLoss(), 'optimizer': Adam ( Parameter Group 0 amsgrad: False betas: (0.9, 0.999) capturable: False differentiable: False eps: 1e-08 foreach: None fused: None lr: 0.001 maximize: False weight_decay: 1e-05 ), 'metrics': {'train': [MulticlassAccuracy(), MulticlassF1Score(), MulticlassPrecision(), MulticlassRecall()], 'val': [MulticlassAccuracy(), MulticlassF1Score(), MulticlassPrecision(), MulticlassRecall()], 'test': [MulticlassAccuracy(), MulticlassF1Score(), MulticlassPrecision(), MulticlassRecall()]}, 'datasets': {'train': Dataset CIFAR10 Number of datapoints: 50000 Root location: ./.datasets/ Split: Train StandardTransform Transform: , 'val': Dataset CIFAR10 Number of datapoints: 10000 Root location: ./.datasets/ Split: Test StandardTransform Transform: , 'test': Dataset CIFAR10 Number of datapoints: 10000 Root location: ./.datasets/ Split: Test StandardTransform Transform: Compose( ToTensor() Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) ), 'predict': Dataset CIFAR10 Number of datapoints: 10000 Root location: ./.datasets/ Split: Test StandardTransform Transform: Compose( ToTensor() Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) )}} set '_mode_=debug' to enter the debugging mode. The above exception was the direct cause of the following exception: ╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮ │ /home/suraj/miniconda3/envs/lighter_test_env/lib/python3.8/runpy.py:194 in _run_module_as_main │ │ │ │ 191 │ main_globals = sys.modules["__main__"].__dict__ │ │ 192 │ if alter_argv: │ │ 193 │ │ sys.argv[0] = mod_spec.origin │ │ ❱ 194 │ return _run_code(code, main_globals, None, │ │ 195 │ │ │ │ │ "__main__", mod_spec) │ │ 196 │ │ 197 def run_module(mod_name, init_globals=None, │ │ │ │ /home/suraj/miniconda3/envs/lighter_test_env/lib/python3.8/runpy.py:87 in _run_code │ │ │ │ 84 │ │ │ │ │ __loader__ = loader, │ │ 85 │ │ │ │ │ __package__ = pkg_name, │ │ 86 │ │ │ │ │ __spec__ = mod_spec) │ │ ❱ 87 │ exec(code, run_globals) │ │ 88 │ return run_globals │ │ 89 │ │ 90 def _run_module_code(code, init_globals=None, │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/__main__.py:31 in │ │ │ │ /home/suraj/miniconda3/envs/lighter_test_env/lib/python3.8/site-packages/fire/core.py:141 in Fire │ │ │ │ /home/suraj/miniconda3/envs/lighter_test_env/lib/python3.8/site-packages/fire/core.py:475 in _Fire │ │ │ │ /home/suraj/miniconda3/envs/lighter_test_env/lib/python3.8/site-packages/fire/core.py:691 in _CallAndUpdateTrace │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/scripts.py:787 in run │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/workflows.py:310 in run │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/workflows.py:344 in _run_expr │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/config_parser.py:290 in get_parsed_content │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/reference_resolver.py:193 in get_resolved_content │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/reference_resolver.py:171 in _resolve_one_item │ │ │ │ /home/suraj/.local/lib/python3.8/site-packages/monai/bundle/config_item.py:295 in instantiate │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ RuntimeError: Failed to instantiate ConfigComponent: {'_target_': 'lighter.LighterSystem', 'batch_size': 512, 'criterion': CrossEntropyLoss(), 'datasets': {'predict': Dataset CIFAR10 Number of datapoints: 10000 Root location: ./.datasets/ Split: Test StandardTransform Transform: Compose( ToTensor() Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) ), 'test': Dataset CIFAR10 Number of datapoints: 10000 Root location: ./.datasets/ Split: Test StandardTransform Transform: Compose( ToTensor() Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) ), 'train': Dataset CIFAR10 Number of datapoints: 50000 Root location: ./.datasets/ Split: Train StandardTransform Transform: , 'val': Dataset CIFAR10 Number of datapoints: 10000 Root location: ./.datasets/ Split: Test StandardTransform Transform: }, 'metrics': {'test': [MulticlassAccuracy(), MulticlassF1Score(), MulticlassPrecision(), MulticlassRecall()], 'train': [MulticlassAccuracy(), MulticlassF1Score(), MulticlassPrecision(), MulticlassRecall()], 'val': [MulticlassAccuracy(), MulticlassF1Score(), MulticlassPrecision(), MulticlassRecall()]}, 'model': EfficientNetBN( (_conv_stem): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), bias=False) (_conv_stem_padding): ConstantPad2d(padding=(0, 1, 0, 1), value=0.0) (_bn0): BatchNorm2d(32, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_blocks): Sequential( (0): Sequential( (0): MBConvBlock( (_expand_conv): Identity() (_expand_conv_padding): Identity() (_bn0): Identity() (_depthwise_conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), groups=32, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(32, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(32, 8, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(8, 32, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(16, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (1): Sequential( (1): MBConvBlock( (_expand_conv): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), groups=96, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(0, 1, 0, 1), value=0.0) (_bn1): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(96, 4, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(4, 96, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (2): MBConvBlock( (_expand_conv): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), groups=144, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (2): Sequential( (3): MBConvBlock( (_expand_conv): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(144, 144, kernel_size=(5, 5), stride=(2, 2), groups=144, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 2, 1, 2), value=0.0) (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (4): MBConvBlock( (_expand_conv): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), groups=240, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (3): Sequential( (5): MBConvBlock( (_expand_conv): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(240, 240, kernel_size=(3, 3), stride=(2, 2), groups=240, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(0, 1, 0, 1), value=0.0) (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(240, 80, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (6): MBConvBlock( (_expand_conv): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (7): MBConvBlock( (_expand_conv): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), groups=480, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(80, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (4): Sequential( (8): MBConvBlock( (_expand_conv): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(480, 480, kernel_size=(5, 5), stride=(1, 1), groups=480, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(480, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(480, 112, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (9): MBConvBlock( (_expand_conv): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (10): MBConvBlock( (_expand_conv): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), groups=672, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (5): Sequential( (11): MBConvBlock( (_expand_conv): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(672, 672, kernel_size=(5, 5), stride=(2, 2), groups=672, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 2, 1, 2), value=0.0) (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (12): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (13): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) (14): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(2, 2, 2, 2), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(192, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) (6): Sequential( (15): MBConvBlock( (_expand_conv): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False) (_expand_conv_padding): Identity() (_bn0): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_depthwise_conv): Conv2d(1152, 1152, kernel_size=(3, 3), stride=(1, 1), groups=1152, bias=False) (_depthwise_conv_padding): ConstantPad2d(padding=(1, 1, 1, 1), value=0.0) (_bn1): BatchNorm2d(1152, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_se_adaptpool): AdaptiveAvgPool2d(output_size=1) (_se_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1)) (_se_reduce_padding): Identity() (_se_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1)) (_se_expand_padding): Identity() (_project_conv): Conv2d(1152, 320, kernel_size=(1, 1), stride=(1, 1), bias=False) (_project_conv_padding): Identity() (_bn2): BatchNorm2d(320, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_swish): MemoryEfficientSwish() ) ) ) (_conv_head): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False) (_conv_head_padding): Identity() (_bn1): BatchNorm2d(1280, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (_avg_pooling): AdaptiveAvgPool2d(output_size=1) (_dropout): Dropout(p=0.2, inplace=False) (_fc): Linear(in_features=1280, out_features=10, bias=True) (_swish): MemoryEfficientSwish() ), 'num_workers': 6, 'optimizer': Adam ( Parameter Group 0 amsgrad: False betas: (0.9, 0.999) capturable: False differentiable: False eps: 1e-08 foreach: None fused: None lr: 0.001 maximize: False weight_decay: 1e-05 ), 'pin_memory': True, 'test': 5}