Upload DetrForObjectDetection

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 +1,303 @@
+{
+  "_name_or_path": "facebook/detr-resnet-50",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "[PAD]",
+    "1": "[UNK]",
+    "2": "[CLS]",
+    "3": "[SEP]",
+    "4": "[MASK]",
+    "5": " ",
+    "6": "A",
+    "7": "B",
+    "8": "C",
+    "9": "D",
+    "10": "E",
+    "11": "F",
+    "12": "G",
+    "13": "H",
+    "14": "I",
+    "15": "J",
+    "16": "K",
+    "17": "L",
+    "18": "M",
+    "19": "N",
+    "20": "O",
+    "21": "P",
+    "22": "Q",
+    "23": "R",
+    "24": "S",
+    "25": "T",
+    "26": "U",
+    "27": "V",
+    "28": "W",
+    "29": "X",
+    "30": "Y",
+    "31": "Z",
+    "32": "a",
+    "33": "b",
+    "34": "c",
+    "35": "d",
+    "36": "e",
+    "37": "f",
+    "38": "g",
+    "39": "h",
+    "40": "i",
+    "41": "j",
+    "42": "k",
+    "43": "l",
+    "44": "m",
+    "45": "n",
+    "46": "o",
+    "47": "p",
+    "48": "q",
+    "49": "r",
+    "50": "s",
+    "51": "t",
+    "52": "u",
+    "53": "v",
+    "54": "w",
+    "55": "x",
+    "56": "y",
+    "57": "z",
+    "58": "\u0410",
+    "59": "\u0411",
+    "60": "\u0412",
+    "61": "\u0413",
+    "62": "\u0414",
+    "63": "\u0415",
+    "64": "\u0416",
+    "65": "\u0417",
+    "66": "\u0418",
+    "67": "\u0419",
+    "68": "\u041a",
+    "69": "\u041b",
+    "70": "\u041c",
+    "71": "\u041d",
+    "72": "\u041e",
+    "73": "\u041f",
+    "74": "\u0420",
+    "75": "\u0421",
+    "76": "\u0422",
+    "77": "\u0423",
+    "78": "\u0424",
+    "79": "\u0425",
+    "80": "\u0426",
+    "81": "\u0427",
+    "82": "\u0428",
+    "83": "\u0429",
+    "84": "\u042b",
+    "85": "\u042c",
+    "86": "\u042d",
+    "87": "\u042e",
+    "88": "\u042f",
+    "89": "\u0430",
+    "90": "\u0431",
+    "91": "\u0432",
+    "92": "\u0433",
+    "93": "\u0434",
+    "94": "\u0435",
+    "95": "\u0436",
+    "96": "\u0437",
+    "97": "\u0438",
+    "98": "\u0439",
+    "99": "\u043a",
+    "100": "\u043b",
+    "101": "\u043c",
+    "102": "\u043d",
+    "103": "\u043e",
+    "104": "\u043f",
+    "105": "\u0440",
+    "106": "\u0441",
+    "107": "\u0442",
+    "108": "\u0443",
+    "109": "\u0444",
+    "110": "\u0445",
+    "111": "\u0446",
+    "112": "\u0447",
+    "113": "\u0448",
+    "114": "\u0449",
+    "115": "\u044a",
+    "116": "\u044b",
+    "117": "\u044c",
+    "118": "\u044d",
+    "119": "\u044e",
+    "120": "\u044f",
+    "121": "\u0451"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    " ": 5,
+    "A": 6,
+    "B": 7,
+    "C": 8,
+    "D": 9,
+    "E": 10,
+    "F": 11,
+    "G": 12,
+    "H": 13,
+    "I": 14,
+    "J": 15,
+    "K": 16,
+    "L": 17,
+    "M": 18,
+    "N": 19,
+    "O": 20,
+    "P": 21,
+    "Q": 22,
+    "R": 23,
+    "S": 24,
+    "T": 25,
+    "U": 26,
+    "V": 27,
+    "W": 28,
+    "X": 29,
+    "Y": 30,
+    "Z": 31,
+    "[CLS]": 2,
+    "[MASK]": 4,
+    "[PAD]": 0,
+    "[SEP]": 3,
+    "[UNK]": 1,
+    "a": 32,
+    "b": 33,
+    "c": 34,
+    "d": 35,
+    "e": 36,
+    "f": 37,
+    "g": 38,
+    "h": 39,
+    "i": 40,
+    "j": 41,
+    "k": 42,
+    "l": 43,
+    "m": 44,
+    "n": 45,
+    "o": 46,
+    "p": 47,
+    "q": 48,
+    "r": 49,
+    "s": 50,
+    "t": 51,
+    "u": 52,
+    "v": 53,
+    "w": 54,
+    "x": 55,
+    "y": 56,
+    "z": 57,
+    "\u0410": 58,
+    "\u0411": 59,
+    "\u0412": 60,
+    "\u0413": 61,
+    "\u0414": 62,
+    "\u0415": 63,
+    "\u0416": 64,
+    "\u0417": 65,
+    "\u0418": 66,
+    "\u0419": 67,
+    "\u041a": 68,
+    "\u041b": 69,
+    "\u041c": 70,
+    "\u041d": 71,
+    "\u041e": 72,
+    "\u041f": 73,
+    "\u0420": 74,
+    "\u0421": 75,
+    "\u0422": 76,
+    "\u0423": 77,
+    "\u0424": 78,
+    "\u0425": 79,
+    "\u0426": 80,
+    "\u0427": 81,
+    "\u0428": 82,
+    "\u0429": 83,
+    "\u042b": 84,
+    "\u042c": 85,
+    "\u042d": 86,
+    "\u042e": 87,
+    "\u042f": 88,
+    "\u0430": 89,
+    "\u0431": 90,
+    "\u0432": 91,
+    "\u0433": 92,
+    "\u0434": 93,
+    "\u0435": 94,
+    "\u0436": 95,
+    "\u0437": 96,
+    "\u0438": 97,
+    "\u0439": 98,
+    "\u043a": 99,
+    "\u043b": 100,
+    "\u043c": 101,
+    "\u043d": 102,
+    "\u043e": 103,
+    "\u043f": 104,
+    "\u0440": 105,
+    "\u0441": 106,
+    "\u0442": 107,
+    "\u0443": 108,
+    "\u0444": 109,
+    "\u0445": 110,
+    "\u0446": 111,
+    "\u0447": 112,
+    "\u0448": 113,
+    "\u0449": 114,
+    "\u044a": 115,
+    "\u044b": 116,
+    "\u044c": 117,
+    "\u044d": 118,
+    "\u044e": 119,
+    "\u044f": 120,
+    "\u0451": 121
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d433c3abbe3e1e3320bba089f052e2169e7892a4dc3fbddfb9acc57a5cc28b
+size 166619244