Upload model

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 +1,77 @@
+{
+  "add_all_frames_to_correct_as_cond": false,
+  "add_tpos_enc_to_obj_ptrs": false,
+  "architectures": [
+    "Sam2Model"
+  ],
+  "backbone_stride": 16,
+  "binarize_mask_from_pts_for_mem_enc": false,
+  "compile_image_encoder": false,
+  "directly_add_no_mem_embed": true,
+  "fixed_no_obj_ptr": true,
+  "image_encoder_config": {
+    "backbone_channel_list": [
+      1152,
+      576,
+      288,
+      144
+    ],
+    "embed_dim": 144,
+    "global_att_blocks": [
+      23,
+      33,
+      43
+    ],
+    "model_type": "",
+    "stages": [
+      2,
+      6,
+      36,
+      4
+    ],
+    "window_pos_embed_bkg_spatial_size": [
+      7,
+      7
+    ],
+    "window_spec": [
+      8,
+      4,
+      16,
+      8
+    ]
+  },
+  "image_size": 1024,
+  "initializer_range": 0.02,
+  "iou_prediction_use_sigmoid": true,
+  "max_cond_frames_in_attn": -1,
+  "max_obj_ptrs_in_encoder": 16,
+  "memory_attention_config": {
+    "model_type": ""
+  },
+  "memory_encoder_config": {
+    "model_type": ""
+  },
+  "memory_temporal_stride_for_eval": 1,
+  "model_type": "sam2",
+  "multimask_max_pt_num": 1,
+  "multimask_min_pt_num": 0,
+  "multimask_output_for_tracking": true,
+  "multimask_output_in_sam": true,
+  "non_overlap_masks_for_mem_enc": false,
+  "num_maskmem": 7,
+  "only_obj_ptrs_in_the_past_for_eval": true,
+  "pred_obj_scores": true,
+  "pred_obj_scores_mlp": true,
+  "proj_tpos_enc_in_obj_ptrs": false,
+  "sam_mask_decoder_extra_args": null,
+  "sigmoid_bias_for_mem_enc": -10,
+  "sigmoid_scale_for_mem_enc": 20,
+  "soft_no_obj_ptr": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_high_res_features_in_sam": true,
+  "use_mask_input_as_output_without_sam": true,
+  "use_mlp_for_obj_ptr_proj": true,
+  "use_multimask_token_for_obj_ptr": true,
+  "use_obj_ptrs_in_encoder": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52414469076aee4a696960350a0213bcad8f906f005b4839dc831162a067666f
+size 897827480