Upload DiffusionDet

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 +1,129 @@
+{
+  "activation": "relu",
+  "alpha": 0.25,
+  "architectures": [
+    "DiffusionDet"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_diffusiondet.DiffusionDetConfig",
+    "AutoModelForObjectDetection": "modeling_diffusiondet.DiffusionDet"
+  },
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "backbone_multiplier": 1.0,
+  "class_weight": 2.0,
+  "deep_supervision": true,
+  "dilation": false,
+  "dim_dynamic": 64,
+  "dim_feedforward": 2048,
+  "dropout": 0.0,
+  "fpn_out_channels": 256,
+  "gamma": 2.0,
+  "giou_weight": 2.0,
+  "hidden_dim": 256,
+  "id2label": {
+    "0": "plane",
+    "1": "ship",
+    "2": "storage-tank",
+    "3": "baseball-diamond",
+    "4": "tennis-court",
+    "5": "basketball-court",
+    "6": "ground-track-field",
+    "7": "harbor",
+    "8": "bridge",
+    "9": "small-vehicle",
+    "10": "large-vehicle",
+    "11": "roundabout",
+    "12": "swimming-pool",
+    "13": "helicopter",
+    "14": "soccer-ball-field",
+    "15": "container-crane"
+  },
+  "l1_weight": 5.0,
+  "label2id": {
+    "baseball-diamond": 3,
+    "basketball-court": 5,
+    "bridge": 8,
+    "container-crane": 15,
+    "ground-track-field": 6,
+    "harbor": 7,
+    "helicopter": 13,
+    "large-vehicle": 10,
+    "plane": 0,
+    "roundabout": 11,
+    "ship": 1,
+    "small-vehicle": 9,
+    "soccer-ball-field": 14,
+    "storage-tank": 2,
+    "swimming-pool": 12,
+    "tennis-court": 4
+  },
+  "model_type": "diffusiondet",
+  "no_object_weight": 0.1,
+  "num_attn_heads": 8,
+  "num_channels": 3,
+  "num_cls": 1,
+  "num_dynamic": 2,
+  "num_heads": 6,
+  "num_proposals": 300,
+  "num_reg": 3,
+  "optimizer": "ADAMW",
+  "ota_k": 5,
+  "pixel_mean": [
+    123.675,
+    116.28,
+    103.53
+  ],
+  "pixel_std": [
+    58.395,
+    57.12,
+    57.375
+  ],
+  "pooler_resolution": 7,
+  "prior_prob": 0.01,
+  "resnet_in_features": [
+    "res2",
+    "res3",
+    "res4",
+    "res5"
+  ],
+  "resnet_out_features": [
+    "res2",
+    "res3",
+    "res4",
+    "res5"
+  ],
+  "roi_head_in_features": [
+    "p2",
+    "p3",
+    "p4",
+    "p5"
+  ],
+  "sample_step": 1,
+  "sampling_ratio": 2,
+  "snr_scale": 2.0,
+  "swin_out_features": [
+    0,
+    1,
+    2,
+    3
+  ],
+  "swin_size": "B",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.0.dev0",
+  "use_fed_loss": false,
+  "use_focal": true,
+  "use_nms": true,
+  "use_pretrained_backbone": true,
+  "use_swin_checkpoint": false,
+  "use_timm_backbone": true
+}

configuration_diffusiondet.py

@@ -0,0 +1,167 @@
+from transformers import PretrainedConfig
+
+from transformers.models.auto import CONFIG_MAPPING
+from transformers.utils.backbone_utils import verify_backbone_config_arguments
+
+from transformers.utils import logging, PushToHubMixin
+
+logger = logging.get_logger(__name__)
+
+class DiffusionDetConfig(PretrainedConfig):
+
+    model_type = "diffusiondet"
+
+    def __init__(
+            self,
+            use_timm_backbone=True,
+            backbone_config=None,
+            num_channels=3,
+            pixel_mean=(123.675, 116.280, 103.530),
+            pixel_std=(58.395, 57.120, 57.375),
+            resnet_out_features=("res2", "res3", "res4", "res5"),
+            resnet_in_features=("res2", "res3", "res4", "res5"),
+            roi_head_in_features=("p2", "p3", "p4", "p5"),
+            fpn_out_channels=256,
+            pooler_resolution=7,
+            sampling_ratio=2,
+            num_proposals=300,
+            num_attn_heads=8,
+            dropout=0.0,
+            dim_feedforward=2048,
+            activation="relu",
+            hidden_dim=256,
+            num_cls=1,
+            num_reg=3,
+            num_heads=6,
+            num_dynamic=2,
+            dim_dynamic=64,
+            class_weight=2.0,
+            giou_weight=2.0,
+            l1_weight=5.0,
+            deep_supervision=True,
+            no_object_weight=0.1,
+            use_focal=True,
+            use_fed_loss=False,
+            alpha=0.25,
+            gamma=2.0,
+            prior_prob=0.01,
+            ota_k=5,
+            snr_scale=2.0,
+            sample_step=1,
+            use_nms=True,
+            swin_size="B",
+            use_swin_checkpoint=False,
+            swin_out_features=(0, 1, 2, 3),
+            optimizer="ADAMW",
+            backbone_multiplier=1.0,
+            backbone='resnet50',
+            use_pretrained_backbone=True,
+            backbone_kwargs=None,
+            dilation=False,
+            **kwargs
+    ):
+        # We default to values which were previously hard-coded in the model. This enables configurability of the config
+        # while keeping the default behavior the same.
+        if use_timm_backbone and backbone_kwargs is None:
+            backbone_kwargs = {}
+            if dilation:
+                backbone_kwargs["output_stride"] = 16
+            backbone_kwargs["out_indices"] = [1, 2, 3, 4]
+            backbone_kwargs["in_chans"] = num_channels
+        # Backwards compatibility
+        elif not use_timm_backbone and backbone in (None, "resnet50"):
+            if backbone_config is None:
+                logger.info("`backbone_config` is `None`. Initializing the config with the default `ResNet` backbone.")
+                backbone_config = CONFIG_MAPPING["resnet"](out_features=["stage4"])
+            elif isinstance(backbone_config, dict):
+                backbone_model_type = backbone_config.get("model_type")
+                config_class = CONFIG_MAPPING[backbone_model_type]
+                backbone_config = config_class.from_dict(backbone_config)
+            backbone = None
+            # set timm attributes to None
+            dilation = None
+
+        verify_backbone_config_arguments(
+            use_timm_backbone=use_timm_backbone,
+            use_pretrained_backbone=use_pretrained_backbone,
+            backbone=backbone,
+            backbone_config=backbone_config,
+            backbone_kwargs=backbone_kwargs,
+        )
+
+        # Auto mapping
+        self.auto_map = {
+            "AutoConfig": "configuration_diffusiondet.DiffusionDetConfig",
+            "AutoModelForObjectDetection": "modeling_diffusiondet.DiffusionDet"
+        }
+
+        # Backbone.
+        self.use_timm_backbone = use_timm_backbone
+        self.backbone_config = backbone_config
+        self.num_channels = num_channels
+        self.backbone = backbone
+        self.use_pretrained_backbone = use_pretrained_backbone
+        self.backbone_kwargs = backbone_kwargs
+        self.dilation = dilation
+        self.fpn_out_channels = fpn_out_channels
+
+        # Model.
+        self.pixel_mean = pixel_mean
+        self.pixel_std = pixel_std
+        self.resnet_out_features = resnet_out_features
+        self.resnet_in_features = resnet_in_features
+        self.roi_head_in_features = roi_head_in_features
+        self.pooler_resolution = pooler_resolution
+        self.sampling_ratio = sampling_ratio
+        self.num_proposals = num_proposals
+
+        # RCNN Head.
+        self.num_attn_heads = num_attn_heads
+        self.dropout = dropout
+        self.dim_feedforward = dim_feedforward
+        self.activation = activation
+        self.hidden_dim = hidden_dim
+        self.num_cls = num_cls
+        self.num_reg = num_reg
+        self.num_heads = num_heads
+
+        # Dynamic Conv.
+        self.num_dynamic = num_dynamic
+        self.dim_dynamic = dim_dynamic
+
+        # Loss.
+        self.class_weight = class_weight
+        self.giou_weight = giou_weight
+        self.l1_weight = l1_weight
+        self.deep_supervision = deep_supervision
+        self.no_object_weight = no_object_weight
+
+        # Focal Loss.
+        self.use_focal = use_focal
+        self.use_fed_loss = use_fed_loss
+        self.alpha = alpha
+        self.gamma = gamma
+        self.prior_prob = prior_prob
+
+        # Dynamic K
+        self.ota_k = ota_k
+
+        # Diffusion
+        self.snr_scale = snr_scale
+        self.sample_step = sample_step
+
+        # Inference
+        self.use_nms = use_nms
+
+        # Swin Backbones
+        self.swin_size = swin_size
+        self.use_swin_checkpoint = use_swin_checkpoint
+        self.swin_out_features = swin_out_features
+
+        # Optimizer.
+        self.optimizer = optimizer
+        self.backbone_multiplier = backbone_multiplier
+
+        self.num_labels = 80
+
+        super().__init__()

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e517fed9e7068145013593fed1b44f53526265d171c484d525571a38dbd251dc
+size 442808528