Upload LayoutElementDetector

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 +1,298 @@
+{
+  "architectures": [
+    "LayoutElementDetector"
+  ],
+  "classes": [
+    "Im_Table",
+    "Paragraph",
+    "Caption",
+    "Table",
+    "Figure",
+    "Equation",
+    "Footer",
+    "Header"
+  ],
+  "input": {
+    "max_size": 1333,
+    "min_size": 800,
+    "model_type": ""
+  },
+  "model": {
+    "anchor_generator": {
+      "aspect_ratios": [
+        [
+          0.5,
+          1.0,
+          2.0
+        ]
+      ],
+      "model_type": "",
+      "offset": 0.0,
+      "sizes": [
+        [
+          32
+        ],
+        [
+          64
+        ],
+        [
+          128
+        ],
+        [
+          256
+        ],
+        [
+          512
+        ]
+      ]
+    },
+    "backbone": {
+      "config": {
+        "_name_or_path": "",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attention_probs_dropout_prob": 0.1,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": 0,
+        "chunk_size_feed_forward": 0,
+        "classifier_dropout": null,
+        "coordinate_size": 128,
+        "cross_attention_hidden_size": null,
+        "decoder_start_token_id": null,
+        "discrete_vae_type": "dall-e",
+        "discrete_vae_weight_path": "",
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": false,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": 2,
+        "exponential_decay_length_penalty": null,
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "has_relative_attention_bias": false,
+        "has_spatial_attention_bias": false,
+        "hidden_act": "gelu",
+        "hidden_dropout_prob": 0.1,
+        "hidden_size": 768,
+        "id2label": {
+          "0": "LABEL_0",
+          "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "input_size": 224,
+        "intermediate_size": 3072,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+          "LABEL_0": 0,
+          "LABEL_1": 1
+        },
+        "layer_norm_eps": 1e-05,
+        "length_penalty": 1.0,
+        "max_2d_position_embeddings": 1024,
+        "max_length": 20,
+        "max_position_embeddings": 514,
+        "max_rel_2d_pos": 256,
+        "max_rel_pos": 128,
+        "mim": false,
+        "min_length": 0,
+        "model_type": "uplayoutlmv3",
+        "no_repeat_ngram_size": 0,
+        "num_attention_heads": 12,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_channels": 3,
+        "num_hidden_layers": 12,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": 1,
+        "patch_size": 16,
+        "position_embedding_type": "absolute",
+        "prefix": null,
+        "problem_type": null,
+        "pruned_heads": {},
+        "rel_2d_pos_bins": 64,
+        "rel_pos_bins": 32,
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "second_input_size": 112,
+        "sep_token_id": null,
+        "shape_size": 128,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "text_embed": true,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1.0,
+        "torch_dtype": "float16",
+        "torchscript": false,
+        "type_vocab_size": 1,
+        "typical_p": 1.0,
+        "use_bfloat16": false,
+        "use_cache": true,
+        "visual_embed": true,
+        "vocab_size": 50265,
+        "wpa_task": false
+      },
+      "drop_path": 0.1,
+      "img_size": [
+        224,
+        224
+      ],
+      "model_type": "",
+      "out_features": [
+        "layer3",
+        "layer5",
+        "layer7",
+        "layer11"
+      ],
+      "pos_type": "abs"
+    },
+    "fpn": {
+      "fuse_type": "sum",
+      "in_features": [
+        "layer3",
+        "layer5",
+        "layer7",
+        "layer11"
+      ],
+      "model_type": "",
+      "out_channels": 256
+    },
+    "mask_on": true,
+    "model_type": "",
+    "pixel_mean": [
+      127.5,
+      127.5,
+      127.5
+    ],
+    "pixel_std": [
+      127.5,
+      127.5,
+      127.5
+    ],
+    "roi_box_cascade_head": {
+      "bbox_reg_weights": [
+        [
+          10.0,
+          10.0,
+          5.0,
+          5.0
+        ],
+        [
+          20.0,
+          20.0,
+          10.0,
+          10.0
+        ],
+        [
+          30.0,
+          30.0,
+          15.0,
+          15.0
+        ]
+      ],
+      "ious": [
+        0.5,
+        0.6,
+        0.7
+      ],
+      "model_type": ""
+    },
+    "roi_box_head": {
+      "cls_agnostic_bbox_reg": true,
+      "fc_dim": 1024,
+      "model_type": "",
+      "num_fc": 2,
+      "pooler_resolution": 7,
+      "pooler_sampling_ratio": 0,
+      "use_sigmoid_ce": false
+    },
+    "roi_heads": {
+      "in_features": [
+        "p2",
+        "p3",
+        "p4",
+        "p5"
+      ],
+      "in_strides": [
+        4,
+        8,
+        16,
+        32
+      ],
+      "iou_labels": [
+        0,
+        1
+      ],
+      "iou_thresholds": [
+        0.5
+      ],
+      "model_type": "",
+      "num_classes": 8,
+      "test_nms_thresh": 0.5,
+      "test_score_thresh": 0.05
+    },
+    "roi_mask_head": {
+      "cls_agnostic_mask": false,
+      "conv_dim": 256,
+      "model_type": "",
+      "num_conv": 4,
+      "pooler_resolution": 14,
+      "pooler_sampling_ratio": 0
+    },
+    "rpn": {
+      "anchor_boundary_thresh": -1,
+      "bbox_reg_weights": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "conv_dims": [
+        -1
+      ],
+      "in_channels": null,
+      "in_features": [
+        "p2",
+        "p3",
+        "p4",
+        "p5",
+        "p6"
+      ],
+      "in_strides": [
+        4,
+        8,
+        16,
+        32,
+        64
+      ],
+      "min_size": 0,
+      "model_type": "",
+      "nms_thresh": 0.7,
+      "post_nms_topk_test": 1000,
+      "pre_nms_topk_test": 1000
+    },
+    "weights": null
+  },
+  "model_type": "",
+  "test": {
+    "detections_per_images": 100,
+    "label_replace_dict": {
+      "Im_Table": "Paragraph"
+    },
+    "model_type": ""
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf4e13b944ac7600bd984e37d19540278cef213d010dad448d7e244b2cec9c1
+size 281989892