Source code for otx.algo.classification.multilabel_models.mobilenet_v3

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

"""MobileNetV3 model implementation."""

from __future__ import annotations

from typing import TYPE_CHECKING, Any

import torch
from torch import Tensor, nn

from otx.algo.classification.backbones import MobileNetV3Backbone
from otx.algo.classification.classifier import ImageClassifier
from otx.algo.classification.heads import MultiLabelNonLinearClsHead
from otx.algo.classification.losses.asymmetric_angular_loss_with_ignore import AsymmetricAngularLossWithIgnore
from otx.algo.classification.necks.gap import GlobalAveragePooling
from otx.algo.utils.support_otx_v1 import OTXv1Helper
from otx.core.data.entity.base import OTXBatchLossEntity
from otx.core.metrics.accuracy import MultiLabelClsMetricCallable
from otx.core.model.base import DataInputParams, DefaultOptimizerCallable, DefaultSchedulerCallable
from otx.core.model.multilabel_classification import OTXMultilabelClsModel
from otx.core.schedulers import LRSchedulerListCallable
from otx.core.types.label import LabelInfoTypes
from otx.data.torch import TorchDataBatch, TorchPredBatch

if TYPE_CHECKING:
    from lightning.pytorch.cli import LRSchedulerCallable, OptimizerCallable

    from otx.core.metrics import MetricCallable


[docs] class MobileNetV3MultilabelCls(OTXMultilabelClsModel): """MobileNetV3 Model for multi-class classification task. Args: label_info (LabelInfoTypes): The label information. data_input_params (DataInputParams): The data input parameters such as input size and normalization. model_name (str, optional): The model name. Defaults to "mobilenetv3_large". optimizer (OptimizerCallable, optional): The optimizer callable. Defaults to DefaultOptimizerCallable. scheduler (LRSchedulerCallable | LRSchedulerListCallable, optional): The learning rate scheduler callable. Defaults to DefaultSchedulerCallable. metric (MetricCallable, optional): The metric callable. Defaults to MultiClassClsMetricCallable. torch_compile (bool, optional): Whether to compile the model using TorchScript. Defaults to False. """ def __init__( self, label_info: LabelInfoTypes, data_input_params: DataInputParams, model_name: str = "mobilenetv3_large", optimizer: OptimizerCallable = DefaultOptimizerCallable, scheduler: LRSchedulerCallable | LRSchedulerListCallable = DefaultSchedulerCallable, metric: MetricCallable = MultiLabelClsMetricCallable, torch_compile: bool = False, ) -> None: super().__init__( label_info=label_info, data_input_params=data_input_params, model_name=model_name, optimizer=optimizer, scheduler=scheduler, metric=metric, torch_compile=torch_compile, ) def _create_model(self, num_classes: int | None = None) -> nn.Module: num_classes = num_classes if num_classes is not None else self.num_classes return ImageClassifier( backbone=MobileNetV3Backbone(mode=self.model_name, input_size=self.data_input_params.input_size), neck=GlobalAveragePooling(dim=2), head=MultiLabelNonLinearClsHead( num_classes=num_classes, in_channels=MobileNetV3Backbone.MV3_CFG[self.model_name]["out_channels"], hid_channels=MobileNetV3Backbone.MV3_CFG[self.model_name]["hid_channels"], normalized=True, activation=nn.PReLU(), ), loss=AsymmetricAngularLossWithIgnore(gamma_pos=0.0, gamma_neg=1.0, reduction="sum"), loss_scale=7.0, )
[docs] def load_from_otx_v1_ckpt(self, state_dict: dict, add_prefix: str = "model.") -> dict: """Load the previous OTX ckpt according to OTX2.0.""" return OTXv1Helper.load_cls_mobilenet_v3_ckpt(state_dict, "multilabel", add_prefix)
def _customize_inputs(self, inputs: TorchDataBatch) -> dict[str, Any]: if self.training: mode = "loss" elif self.explain_mode: mode = "explain" else: mode = "predict" return { "images": inputs.images, "labels": torch.stack(inputs.labels), "imgs_info": inputs.imgs_info, "mode": mode, } def _customize_outputs( self, outputs: Any, # noqa: ANN401 inputs: TorchDataBatch, ) -> TorchPredBatch | OTXBatchLossEntity: if self.training: return OTXBatchLossEntity(loss=outputs) # To list, batch-wise logits = outputs if isinstance(outputs, torch.Tensor) else outputs["logits"] scores = torch.unbind(logits, 0) return TorchPredBatch( batch_size=inputs.batch_size, images=inputs.images, imgs_info=inputs.imgs_info, scores=list(scores), labels=list(logits.argmax(-1, keepdim=True).unbind(0)), )
[docs] def forward_for_tracing(self, image: Tensor) -> Tensor | dict[str, Tensor]: """Model forward function used for the model tracing during model exportation.""" if self.explain_mode: return self.model(images=image, mode="explain") return self.model(images=image, mode="tensor")