Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,15 @@
+{
+  "architectures": [
+    "RetinaNetModelForObjectDetection"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_retinanet.RetinaNetConfig",
+    "AutoModelForObjectDetection": "modeling_retinanet.RetinaNetModelForObjectDetection"
+  },
+  "model_type": "retinanet",
+  "num_classes": null,
+  "pretrained": true,
+  "pretrained_backbone": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0"
+}

configuration_retinanet.py

@@ -0,0 +1,43 @@
+from transformers.configuration_utils import PretrainedConfig
+from optimum.exporters.onnx.model_configs import ViTOnnxConfig
+from typing import Optional, Dict
+
+class RetinaNetConfig(PretrainedConfig):
+    model_type = 'retinanet'
+
+    def __init__(
+            self,
+            pretrained: bool = False,
+            pretrained_backbone: bool = False,
+            num_classes: Optional[int] = None,
+            **kwargs
+        ):
+        
+        self.num_classes = num_classes
+        self.pretrained = pretrained
+        self.pretrained_backbone = pretrained_backbone
+       
+        super().__init__(**kwargs)
+
+class RetinaNetOnnxConfig(ViTOnnxConfig):
+    @property
+    def inputs(self) -> Dict[str, Dict[int, str]]:
+        return {
+            "pixel_values": {0: "batch_size", 1: "num_channels", 2: "height", 3: "width"},
+            "image_sizes": {0: "batch_size", 1: "image_size"}
+        }
+
+    @property
+    def outputs(self) -> Dict[str, Dict[int, str]]:
+        common_outputs = super().outputs 
+
+        if self.task == "object-detection":
+            common_outputs["logits"] = {0: "batch_size", 1: "num_queries", 2: "num_classes"}
+            common_outputs["pred_boxes"] = {0: "batch_size", 1: "num_queries", 2: "coordinates"}
+        
+        return common_outputs
+    
+__all__ = [
+    'RetinaNetConfig',
+    'RetinaNetOnnxConfig'
+]

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037ef1efd08128649889145dbe95566f4ca09b44c4c421cbb7ee1e314a7de96f
+size 136518212

modeling_retinanet.py

@@ -0,0 +1,104 @@
+import torch
+from dataclasses import dataclass
+from torchvision.models import ResNet50_Weights
+from torchvision.models.detection import retinanet_resnet50_fpn, RetinaNet_ResNet50_FPN_Weights
+from torchvision.models.detection.anchor_utils import AnchorGenerator
+
+from transformers import PreTrainedModel
+from transformers.utils import ModelOutput
+from typing import OrderedDict, List, Tuple
+
+from configuration_retinanet import RetinaNetConfig
+
+def _default_anchorgen():
+        anchor_sizes = tuple((x, int(x * 2 ** (1.0 / 3)), int(x * 2 ** (2.0 / 3))) for x in [32, 64, 128, 256, 512])
+        aspect_ratios = ((0.5, 1.0, 2.0),) * len(anchor_sizes)
+        anchor_generator = RetinaNetAnchorGenerator(anchor_sizes, aspect_ratios)
+        return anchor_generator
+
+@dataclass
+class RetinaNetObjectDetectionOutput(ModelOutput):
+    logits: torch.FloatTensor = None
+    pred_boxes: torch.FloatTensor = None
+    image_sizes: List[Tuple] = None
+    anchors: List[torch.Tensor] = None
+    features: List[torch.Tensor] = None
+
+class RetinaNetAnchorGenerator(AnchorGenerator):
+    def __init__(
+            self,
+            sizes=((128, 256, 512),),
+            aspect_ratios=((0.5, 1.0, 2.0),)
+        ):
+        super().__init__(sizes, aspect_ratios)
+
+    def forward(self, pixel_values: torch.Tensor, feature_maps: List[torch.Tensor]) -> List[torch.Tensor]:
+        grid_sizes = [feature_map.shape[-2:] for feature_map in feature_maps]
+        image_size = pixel_values.shape[-2:]
+        dtype, device = feature_maps[0].dtype, feature_maps[0].device
+        strides = [
+            [
+                torch.empty((), dtype=torch.int64, device=device).fill_(image_size[0] // g[0]),
+                torch.empty((), dtype=torch.int64, device=device).fill_(image_size[1] // g[1]),
+            ]
+            for g in grid_sizes
+        ]
+        self.set_cell_anchors(dtype, device)
+        anchors_over_all_feature_maps = self.grid_anchors(grid_sizes, strides)
+        anchors: List[List[torch.Tensor]] = []
+        for _ in range(pixel_values.shape[0]):
+            anchors_in_image = [anchors_per_feature_map for anchors_per_feature_map in anchors_over_all_feature_maps]
+            anchors.append(anchors_in_image)
+        anchors = [torch.cat(anchors_per_image) for anchors_per_image in anchors]
+        return anchors
+
+class RetinaNetModelForObjectDetection(PreTrainedModel):
+    config_class = RetinaNetConfig
+
+    def __init__(self, config):
+        super().__init__(config)
+
+        self.config = config
+        
+        model_config = {
+            'weights': None,
+            'weights_backbone': None,
+            'num_classes': None
+        }
+
+        if config.pretrained:
+            model_config['weights'] = RetinaNet_ResNet50_FPN_Weights.DEFAULT
+        else:
+            model_config['num_classes'] = config.num_classes
+            if config.pretrained_backbone:
+                model_config['weights_backbone'] = ResNet50_Weights.DEFAULT
+           
+        self.model = retinanet_resnet50_fpn(**model_config)
+        self.model.anchor_generator = _default_anchorgen()
+
+    def forward(self, pixel_values, image_sizes, labels=None):
+        if labels is not None:
+            raise NotImplementedError
+
+        features = self.model.backbone(pixel_values)
+        if isinstance(features, torch.Tensor):
+            features = OrderedDict([("0", features)])
+        features = list(features.values())
+
+        # compute the retinanet heads outputs using the features
+        head_outputs = self.model.head(features)
+
+        # create the set of anchors
+        anchors = self.model.anchor_generator(pixel_values, features)
+
+        return RetinaNetObjectDetectionOutput(
+            logits=head_outputs['cls_logits'],
+            pred_boxes=head_outputs['bbox_regression'],
+            image_sizes=image_sizes,
+            anchors=anchors, 
+            features=features
+        )
+    
+__all__ = [
+    "RetinaNetModelForObjectDetection"
+]