modeling_resnet.py

"ref:https://huggingface.co/docs/transformers/custom_models#sharing-custom-models"
from transformers import PreTrainedModel
from timm.models.resnet import BasicBlock, Bottleneck, ResNet
from configuration_resnet import ResnetConfig
from transformers import AutoConfig, AutoModel, AutoModelForImageClassification
import torch
import timm


BLOCK_MAPPING = {"basic": BasicBlock, "bottleneck": Bottleneck}

class ResnetModel(PreTrainedModel):
    config_class = ResnetConfig

    def __init__(self, config):
        super().__init__(config)
        block_layer = BLOCK_MAPPING[config.block_type]
        self.model = ResNet(
            block_layer,
            config.layers,
            num_classes=config.num_classes,
            in_chans=config.input_channels,
            cardinality=config.cardinality,
            base_width=config.base_width,
            stem_width=config.stem_width,
            stem_type=config.stem_type,
            avg_down=config.avg_down,
        )

    def forward(self, tensor):
        return self.model.forward_features(tensor)


class ResnetModelForImageClassification(PreTrainedModel):
    config_class = ResnetConfig

    def __init__(self, config):
        super().__init__(config)
        block_layer = BLOCK_MAPPING[config.block_type]
        self.model = ResNet(
            block_layer,
            config.layers,
            num_classes=config.num_classes,
            in_chans=config.input_channels,
            cardinality=config.cardinality,
            base_width=config.base_width,
            stem_width=config.stem_width,
            stem_type=config.stem_type,
            avg_down=config.avg_down,
        )

    def forward(self, tensor, labels=None):
        logits = self.model(tensor)
        if labels is not None:
            loss = torch.nn.cross_entropy(logits, labels)
            return {"loss": loss, "logits": logits}
        return {"logits": logits}
    
#  create a resnet50d config and save it
resnet50d_config = ResnetConfig(block_type="bottleneck", stem_width=32, stem_type="deep", avg_down=True)
resnet50d_config.save_pretrained("/root/code/Huggingface_Toturials/resnet_model/custom-resnet")

#  reload your config with the from_pretrained method
resnet50d_config = ResnetConfig.from_pretrained("/root/code/Huggingface_Toturials/resnet_model/custom-resnet")

# creat a model
resnet50d = ResnetModelForImageClassification(resnet50d_config)

# use the pretrained version of the resnet50d
pretrained_model = timm.create_model("resnet50d", pretrained=True)
resnet50d.model.load_state_dict(pretrained_model.state_dict())

# add config and model to the auto classes
AutoConfig.register("resnet_demo", ResnetConfig)
AutoModel.register(ResnetConfig, ResnetModel)
AutoModelForImageClassification.register(ResnetConfig, ResnetModelForImageClassification)