Add TF ResNet model

docs/source/en/index.mdx

@@ -263,7 +263,7 @@ Flax), PyTorch, and/or TensorFlow.
 |          Reformer           |       ✅       |       ✅       |       ✅        |         ❌         |      ❌      |
 |           RegNet            |       ❌       |       ❌       |       ✅        |         ❌         |      ❌      |
 |           RemBERT           |       ✅       |       ✅       |       ✅        |         ✅         |      ❌      |
-|           ResNet            |       ❌       |       ❌       |       ✅        |         ❌         |      ❌      |
+|           ResNet            |       ❌       |       ❌       |       ✅        |         ✅         |      ❌      |
 |          RetriBERT          |       ✅       |       ✅       |       ✅        |         ❌         |      ❌      |
 |           RoBERTa           |       ✅       |       ✅       |       ✅        |         ✅         |      ✅      |
 |          RoFormer           |       ✅       |       ✅       |       ✅        |         ✅         |      ✅      |

docs/source/en/model_doc/resnet.mdx

@@ -31,7 +31,7 @@ The figure below illustrates the architecture of ResNet. Taken from the [origina
 
 <img width="600" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/resnet_architecture.png"/>
 
-This model was contributed by [Francesco](https://huggingface.co/Francesco). The original code can be found [here](https://github.com/KaimingHe/deep-residual-networks).
+This model was contributed by [Francesco](https://huggingface.co/Francesco). The TensorFlow version of this model was added by [amyeroberts](https://huggingface.co/amyeroberts). The original code can be found [here](https://github.com/KaimingHe/deep-residual-networks).
 
 ## ResNetConfig
 
@@ -47,4 +47,16 @@ This model was contributed by [Francesco](https://huggingface.co/Francesco). The
 ## ResNetForImageClassification
 
 [[autodoc]] ResNetForImageClassification
-    - forward
+    - forward
+
+
+## TFResNetModel
+
+[[autodoc]] TFResNetModel
+    - call
+
+
+## TFResNetForImageClassification
+
+[[autodoc]] TFResNetForImageClassification
+    - call

src/transformers/__init__.py

@@ -2293,6 +2293,14 @@
             "TFRemBertPreTrainedModel",
         ]
     )
+    _import_structure["models.resnet"].extend(
+        [
+            "TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST",
+            "TFResNetForImageClassification",
+            "TFResNetModel",
+            "TFResNetPreTrainedModel",
+        ]
+    )
     _import_structure["models.roberta"].extend(
         [
             "TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST",
@@ -4563,6 +4571,12 @@
             TFRemBertModel,
             TFRemBertPreTrainedModel,
         )
+        from .models.resnet import (
+            TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST,
+            TFResNetForImageClassification,
+            TFResNetModel,
+            TFResNetPreTrainedModel,
+        )
         from .models.roberta import (
             TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_LIST,
             TFRobertaForCausalLM,

src/transformers/modeling_tf_outputs.py

@@ -46,6 +46,25 @@ class TFBaseModelOutput(ModelOutput):
     attentions: Optional[Tuple[tf.Tensor]] = None
 
 
+@dataclass
+class TFBaseModelOutputWithNoAttention(ModelOutput):
+    """
+    Base class for model's outputs, with potential hidden states.
+
+    Args:
+        last_hidden_state (`tf.Tensor` of shape `(batch_size, num_channels, height, width)`):
+            Sequence of hidden-states at the output of the last layer of the model.
+        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
+            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
+            the output of each layer) of shape `(batch_size, num_channels, height, width)`.
+
+            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
+    """
+
+    last_hidden_state: tf.Tensor = None
+    hidden_states: Optional[Tuple[tf.Tensor, ...]] = None
+
+
 @dataclass
 class TFBaseModelOutputWithPooling(ModelOutput):
     """
@@ -80,6 +99,28 @@ class TFBaseModelOutputWithPooling(ModelOutput):
     attentions: Optional[Tuple[tf.Tensor]] = None
 
 
+@dataclass
+class TFBaseModelOutputWithPoolingAndNoAttention(ModelOutput):
+    """
+    Base class for model's outputs that also contains a pooling of the last hidden states.
+
+    Args:
+        last_hidden_state (`tf.Tensor` of shape `(batch_size, num_channels, height, width)`):
+            Sequence of hidden-states at the output of the last layer of the model.
+        pooler_output (`tf.Tensor` of shape `(batch_size, hidden_size)`):
+            Last layer hidden-state after a pooling operation on the spatial dimensions.
+        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
+            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
+            the output of each layer) of shape `(batch_size, num_channels, height, width)`.
+
+            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
+    """
+
+    last_hidden_state: tf.Tensor = None
+    pooler_output: tf.Tensor = None
+    hidden_states: Optional[Tuple[tf.Tensor, ...]] = None
+
+
 @dataclass
 class TFBaseModelOutputWithPoolingAndCrossAttentions(ModelOutput):
     """
@@ -825,3 +866,24 @@ class TFSequenceClassifierOutputWithPast(ModelOutput):
     past_key_values: Optional[List[tf.Tensor]] = None
     hidden_states: Optional[Tuple[tf.Tensor]] = None
     attentions: Optional[Tuple[tf.Tensor]] = None
+
+
+@dataclass
+class TFImageClassifierOutputWithNoAttention(ModelOutput):
+    """
+    Base class for outputs of image classification models.
+
+    Args:
+        loss (`tf.Tensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
+            Classification (or regression if config.num_labels==1) loss.
+        logits (`tf.Tensor` of shape `(batch_size, config.num_labels)`):
+            Classification (or regression if config.num_labels==1) scores (before SoftMax).
+        hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
+            Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for
+            the output of each stage) of shape `(batch_size, num_channels, height, width)`. Hidden-states (also called
+            feature maps) of the model at the output of each stage.
+    """
+
+    loss: Optional[tf.Tensor] = None
+    logits: tf.Tensor = None
+    hidden_states: Optional[Tuple[tf.Tensor, ...]] = None

src/transformers/models/auto/modeling_tf_auto.py

@@ -63,6 +63,7 @@
         ("opt", "TFOPTModel"),
         ("pegasus", "TFPegasusModel"),
         ("rembert", "TFRemBertModel"),
+        ("resnet", "TFResNetModel"),
         ("roberta", "TFRobertaModel"),
         ("roformer", "TFRoFormerModel"),
         ("speech_to_text", "TFSpeech2TextModel"),
@@ -173,6 +174,7 @@
         # Model for Image-classsification
         ("convnext", "TFConvNextForImageClassification"),
         ("data2vec-vision", "TFData2VecVisionForImageClassification"),
+        ("resnet", "TFResNetForImageClassification"),
         ("swin", "TFSwinForImageClassification"),
         ("vit", "TFViTForImageClassification"),
     ]

src/transformers/models/resnet/__init__.py

@@ -18,7 +18,7 @@
 from typing import TYPE_CHECKING
 
 # rely on isort to merge the imports
-from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_torch_available
+from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_tf_available, is_torch_available
 
 
 _import_structure = {
@@ -38,6 +38,19 @@
         "ResNetPreTrainedModel",
     ]
 
+try:
+    if not is_tf_available():
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    pass
+else:
+    _import_structure["modeling_tf_resnet"] = [
+        "TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST",
+        "TFResNetForImageClassification",
+        "TFResNetModel",
+        "TFResNetPreTrainedModel",
+    ]
+
 
 if TYPE_CHECKING:
     from .configuration_resnet import RESNET_PRETRAINED_CONFIG_ARCHIVE_MAP, ResNetConfig, ResNetOnnxConfig
@@ -55,6 +68,19 @@
             ResNetPreTrainedModel,
         )
 
+    try:
+        if not is_tf_available():
+            raise OptionalDependencyNotAvailable()
+    except OptionalDependencyNotAvailable:
+        pass
+    else:
+        from .modeling_tf_resnet import (
+            TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST,
+            TFResNetForImageClassification,
+            TFResNetModel,
+            TFResNetPreTrainedModel,
+        )
+
 
 else:
     import sys