Upload VitPoseForPoseEstimation

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 +1,171 @@
+{
+  "architectures": [
+    "VitPoseForPoseEstimation"
+  ],
+  "backbone": null,
+  "backbone_config": {
+    "hidden_size": 1024,
+    "model_type": "vitpose_backbone",
+    "num_attention_heads": 16,
+    "num_experts": 6,
+    "num_hidden_layers": 24,
+    "out_features": [
+      "stage24"
+    ],
+    "out_indices": [
+      24
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6",
+      "stage7",
+      "stage8",
+      "stage9",
+      "stage10",
+      "stage11",
+      "stage12",
+      "stage13",
+      "stage14",
+      "stage15",
+      "stage16",
+      "stage17",
+      "stage18",
+      "stage19",
+      "stage20",
+      "stage21",
+      "stage22",
+      "stage23",
+      "stage24"
+    ]
+  },
+  "backbone_kwargs": null,
+  "edges": [
+    [
+      15,
+      13
+    ],
+    [
+      13,
+      11
+    ],
+    [
+      16,
+      14
+    ],
+    [
+      14,
+      12
+    ],
+    [
+      11,
+      12
+    ],
+    [
+      5,
+      11
+    ],
+    [
+      6,
+      12
+    ],
+    [
+      5,
+      6
+    ],
+    [
+      5,
+      7
+    ],
+    [
+      6,
+      8
+    ],
+    [
+      7,
+      9
+    ],
+    [
+      8,
+      10
+    ],
+    [
+      1,
+      2
+    ],
+    [
+      0,
+      1
+    ],
+    [
+      0,
+      2
+    ],
+    [
+      1,
+      3
+    ],
+    [
+      2,
+      4
+    ],
+    [
+      3,
+      5
+    ],
+    [
+      4,
+      6
+    ]
+  ],
+  "id2label": {
+    "0": "Nose",
+    "1": "L_Eye",
+    "2": "R_Eye",
+    "3": "L_Ear",
+    "4": "R_Ear",
+    "5": "L_Shoulder",
+    "6": "R_Shoulder",
+    "7": "L_Elbow",
+    "8": "R_Elbow",
+    "9": "L_Wrist",
+    "10": "R_Wrist",
+    "11": "L_Hip",
+    "12": "R_Hip",
+    "13": "L_Knee",
+    "14": "R_Knee",
+    "15": "L_Ankle",
+    "16": "R_Ankle"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "L_Ankle": 15,
+    "L_Ear": 3,
+    "L_Elbow": 7,
+    "L_Eye": 1,
+    "L_Hip": 11,
+    "L_Knee": 13,
+    "L_Shoulder": 5,
+    "L_Wrist": 9,
+    "Nose": 0,
+    "R_Ankle": 16,
+    "R_Ear": 4,
+    "R_Elbow": 8,
+    "R_Eye": 2,
+    "R_Hip": 12,
+    "R_Knee": 14,
+    "R_Shoulder": 6,
+    "R_Wrist": 10
+  },
+  "model_type": "vitpose",
+  "scale_factor": 4,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.dev0",
+  "use_pretrained_backbone": false,
+  "use_simple_decoder": false,
+  "use_timm_backbone": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b249f74fca7c90b94adb1ebcdbb32cb424fb4fb3c8c40f54a050ccce972643f
+size 1737705492