Add config from convert_rt_detr_original_pytorch_checkpoint_to_pytorch.py

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 +1,273 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": [
+    640,
+    640
+  ],
+  "architectures": [
+    "RTDetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "batch_norm_eps": 1e-05,
+  "box_noise_scale": 1.0,
+  "d_model": 256,
+  "decoder_activation_function": "relu",
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 1024,
+  "decoder_in_channels": [
+    384,
+    384,
+    384
+  ],
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "depths": [
+    3,
+    4,
+    23,
+    3
+  ],
+  "disable_custom_kernels": true,
+  "downsample_in_bottleneck": false,
+  "downsample_in_first_stage": false,
+  "dropout": 0.0,
+  "embedding_size": 64,
+  "encode_proj_layers": [
+    2
+  ],
+  "encoder_activation_function": "gelu",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_hidden_dim": 384,
+  "encoder_in_channels": [
+    512,
+    1024,
+    2048
+  ],
+  "encoder_layers": 1,
+  "eos_coefficient": 0.0001,
+  "eval_size": null,
+  "feat_strides": [
+    8,
+    16,
+    32
+  ],
+  "focal_loss_alpha": 0.75,
+  "focal_loss_gamma": 2.0,
+  "hidden_act": "relu",
+  "hidden_expansion": 1.0,
+  "hidden_sizes": [
+    256,
+    512,
+    1024,
+    2048
+  ],
+  "id2label": {
+    "0": "person",
+    "1": "bicycle",
+    "2": "car",
+    "3": "motorbike",
+    "4": "aeroplane",
+    "5": "bus",
+    "6": "train",
+    "7": "truck",
+    "8": "boat",
+    "9": "traffic light",
+    "10": "fire hydrant",
+    "11": "stop sign",
+    "12": "parking meter",
+    "13": "bench",
+    "14": "bird",
+    "15": "cat",
+    "16": "dog",
+    "17": "horse",
+    "18": "sheep",
+    "19": "cow",
+    "20": "elephant",
+    "21": "bear",
+    "22": "zebra",
+    "23": "giraffe",
+    "24": "backpack",
+    "25": "umbrella",
+    "26": "handbag",
+    "27": "tie",
+    "28": "suitcase",
+    "29": "frisbee",
+    "30": "skis",
+    "31": "snowboard",
+    "32": "sports ball",
+    "33": "kite",
+    "34": "baseball bat",
+    "35": "baseball glove",
+    "36": "skateboard",
+    "37": "surfboard",
+    "38": "tennis racket",
+    "39": "bottle",
+    "40": "wine glass",
+    "41": "cup",
+    "42": "fork",
+    "43": "knife",
+    "44": "spoon",
+    "45": "bowl",
+    "46": "banana",
+    "47": "apple",
+    "48": "sandwich",
+    "49": "orange",
+    "50": "broccoli",
+    "51": "carrot",
+    "52": "hot dog",
+    "53": "pizza",
+    "54": "donut",
+    "55": "cake",
+    "56": "chair",
+    "57": "sofa",
+    "58": "pottedplant",
+    "59": "bed",
+    "60": "diningtable",
+    "61": "toilet",
+    "62": "tvmonitor",
+    "63": "laptop",
+    "64": "mouse",
+    "65": "remote",
+    "66": "keyboard",
+    "67": "cell phone",
+    "68": "microwave",
+    "69": "oven",
+    "70": "toaster",
+    "71": "sink",
+    "72": "refrigerator",
+    "73": "book",
+    "74": "clock",
+    "75": "vase",
+    "76": "scissors",
+    "77": "teddy bear",
+    "78": "hair drier",
+    "79": "toothbrush"
+  },
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "aeroplane": 4,
+    "apple": 47,
+    "backpack": 24,
+    "banana": 46,
+    "baseball bat": 34,
+    "baseball glove": 35,
+    "bear": 21,
+    "bed": 59,
+    "bench": 13,
+    "bicycle": 1,
+    "bird": 14,
+    "boat": 8,
+    "book": 73,
+    "bottle": 39,
+    "bowl": 45,
+    "broccoli": 50,
+    "bus": 5,
+    "cake": 55,
+    "car": 2,
+    "carrot": 51,
+    "cat": 15,
+    "cell phone": 67,
+    "chair": 56,
+    "clock": 74,
+    "cow": 19,
+    "cup": 41,
+    "diningtable": 60,
+    "dog": 16,
+    "donut": 54,
+    "elephant": 20,
+    "fire hydrant": 10,
+    "fork": 42,
+    "frisbee": 29,
+    "giraffe": 23,
+    "hair drier": 78,
+    "handbag": 26,
+    "horse": 17,
+    "hot dog": 52,
+    "keyboard": 66,
+    "kite": 33,
+    "knife": 43,
+    "laptop": 63,
+    "microwave": 68,
+    "motorbike": 3,
+    "mouse": 64,
+    "orange": 49,
+    "oven": 69,
+    "parking meter": 12,
+    "person": 0,
+    "pizza": 53,
+    "pottedplant": 58,
+    "refrigerator": 72,
+    "remote": 65,
+    "sandwich": 48,
+    "scissors": 76,
+    "sheep": 18,
+    "sink": 71,
+    "skateboard": 36,
+    "skis": 30,
+    "snowboard": 31,
+    "sofa": 57,
+    "spoon": 44,
+    "sports ball": 32,
+    "stop sign": 11,
+    "suitcase": 28,
+    "surfboard": 37,
+    "teddy bear": 77,
+    "tennis racket": 38,
+    "tie": 27,
+    "toaster": 70,
+    "toilet": 61,
+    "toothbrush": 79,
+    "traffic light": 9,
+    "train": 6,
+    "truck": 7,
+    "tvmonitor": 62,
+    "umbrella": 25,
+    "vase": 75,
+    "wine glass": 40,
+    "zebra": 22
+  },
+  "label_noise_ratio": 0.5,
+  "layer_norm_eps": 1e-05,
+  "layer_type": "bottleneck",
+  "learn_initial_query": false,
+  "matcher_alpha": 0.25,
+  "matcher_bbox_cost": 5.0,
+  "matcher_class_cost": 2.0,
+  "matcher_gamma": 2.0,
+  "matcher_giou_cost": 2.0,
+  "model_type": "rt_detr",
+  "normalize_before": false,
+  "num_channels": 3,
+  "num_denoising": 100,
+  "num_feature_levels": 3,
+  "num_queries": 300,
+  "out_features": [
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "out_indices": [
+    2,
+    3,
+    4
+  ],
+  "positional_encoding_temperature": 10000,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_focal_loss": true,
+  "weight_loss_bbox": 5.0,
+  "weight_loss_giou": 2.0,
+  "weight_loss_vfl": 1.0,
+  "with_box_refine": true
+}