Upload VINE model - config

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 +1,33 @@
+{
+  "_device": "cpu",
+  "alpha": 0.5,
+  "auto_map": {
+    "AutoConfig": "vine_config.VineConfig"
+  },
+  "bbox_min_dim": 5,
+  "box_threshold": 0.35,
+  "debug_visualizations": false,
+  "hidden_dim": 768,
+  "interested_object_pairs": [],
+  "local_dir": null,
+  "local_filename": null,
+  "max_video_length": 100,
+  "model_file": null,
+  "model_name": "openai/clip-vit-base-patch32",
+  "model_repo": "KevinX-Penn28/testing",
+  "model_type": "vine",
+  "multi_class": false,
+  "num_top_pairs": 18,
+  "output_logit": false,
+  "return_flattened_segments": false,
+  "return_valid_pairs": false,
+  "segmentation_method": "grounding_dino_sam2",
+  "target_fps": 1,
+  "text_threshold": 0.25,
+  "topk_cate": 3,
+  "transformers_version": "4.57.2",
+  "use_hf_repo": true,
+  "visualization_dir": null,
+  "visualize": false,
+  "white_alpha": 0.8
+}

vine_config.py

@@ -0,0 +1,108 @@
+import torch
+from transformers import PretrainedConfig
+from typing import List, Optional, Dict, Any, Tuple
+from pathlib import Path
+
+
+class VineConfig(PretrainedConfig):
+    """
+    Configuration class for VINE (Video Understanding with Natural Language) model.
+    
+    VINE is a video understanding model that processes categorical (object class names),
+    unary keywords (actions on one object), and binary keywords (relations between two objects),
+    and returns probability distributions over all of them when passed a video.
+    
+    Args:
+        model_name (str): The CLIP model name to use as backbone. Default: "openai/clip-vit-large-patch14-336"
+        hidden_dim (int): Hidden dimension size. Default: 768
+        num_top_pairs (int): Number of top object pairs to consider. Default: 10
+        segmentation_method (str): Segmentation method to use ("sam2" or "grounding_dino_sam2"). Default: "grounding_dino_sam2"
+        box_threshold (float): Box threshold for Grounding DINO. Default: 0.35
+        text_threshold (float): Text threshold for Grounding DINO. Default: 0.25
+        target_fps (int): Target FPS for video processing. Default: 1
+        alpha (float): Alpha value for object extraction. Default: 0.5
+        white_alpha (float): White alpha value for background blending. Default: 0.8
+        topk_cate (int): Top-k categories to return. Default: 3
+        multi_class (bool): Whether to use multi-class classification. Default: False
+        output_logit (bool): Whether to output logits instead of probabilities. Default: False
+        max_video_length (int): Maximum number of frames to process. Default: 100
+        bbox_min_dim (int): Minimum bounding box dimension. Default: 5
+        visualize (bool): Whether to visualize results. Default: False
+        visualization_dir (str, optional): Directory to save visualizations. Default: None
+        debug_visualizations (bool): Whether to save debug visualizations. Default: False
+        return_flattened_segments (bool): Whether to return flattened segments. Default: False
+        return_valid_pairs (bool): Whether to return valid object pairs. Default: False
+        interested_object_pairs (List[Tuple[int, int]], optional): List of interested object pairs
+    """
+    
+    model_type = "vine"
+    
+    def __init__(
+        self,
+        model_name: str = "openai/clip-vit-base-patch32",
+        hidden_dim = 768,
+        
+        use_hf_repo: bool = True,
+        model_repo: Optional[str] = "KevinX-Penn28/testing",
+        model_file: Optional[str] = None,
+        local_dir: Optional[str] = str(Path(__file__).resolve().parent),
+        local_filename: Optional[str] = "laser_model_v1.pkl",        
+        
+        num_top_pairs: int = 18,
+        segmentation_method: str = "grounding_dino_sam2",
+        box_threshold: float = 0.35,
+        text_threshold: float = 0.25,
+        target_fps: int = 1,
+        alpha: float = 0.5,
+        white_alpha: float = 0.8,
+        topk_cate: int = 3,
+        multi_class: bool = False,
+        output_logit: bool = False,
+        max_video_length: int = 100,
+        bbox_min_dim: int = 5,
+        visualize: bool = False,
+        visualization_dir: Optional[str] = None,
+        return_flattened_segments: bool = False,
+        return_valid_pairs: bool = False,
+        interested_object_pairs: Optional[List[Tuple[int, int]]] = None,
+        debug_visualizations: bool = False,
+        device: Optional[str | int] = None,
+        **kwargs
+    ):
+        self.model_name = model_name
+        self.use_hf_repo = use_hf_repo
+        if use_hf_repo:
+            self.model_repo = model_repo
+            self.model_file = model_file
+            self.local_dir = None
+            self.local_filename = None
+        else:
+            self.model_repo = None
+            self.model_file = None
+            self.local_dir = local_dir
+            self.local_filename = local_filename
+        self.hidden_dim = hidden_dim
+        self.num_top_pairs = num_top_pairs
+        self.segmentation_method = segmentation_method
+        self.box_threshold = box_threshold
+        self.text_threshold = text_threshold
+        self.target_fps = target_fps
+        self.alpha = alpha
+        self.white_alpha = white_alpha
+        self.topk_cate = topk_cate
+        self.multi_class = multi_class
+        self.output_logit = output_logit
+        self.max_video_length = max_video_length
+        self.bbox_min_dim = bbox_min_dim
+        self.visualize = visualize
+        self.visualization_dir = visualization_dir
+        self.return_flattened_segments = return_flattened_segments
+        self.return_valid_pairs = return_valid_pairs
+        self.interested_object_pairs = interested_object_pairs or []
+        self.debug_visualizations = debug_visualizations
+        if device is int:
+            self._device = f"cuda:{device}" if torch.cuda.is_available() else "cpu"
+        else:
+            self._device = device or ("cuda" if torch.cuda.is_available() else "cpu")
+
+        super().__init__(**kwargs)