timm requirement

README.md

@@ -1,3 +1,20 @@
 ---
 license: mit
+widget:
+- src: https://documentation.tricentis.com/tosca/1420/en/content/tbox/images/table.png
+  example_title: Table
 ---
+
+# Table Transformer (fine-tuned for Table Structure Recognition) 
+
+Table Transformer (DETR) model trained on PubTables1M. It was introduced in the paper [PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents](https://arxiv.org/abs/2110.00061) by Smock et al. and first released in [this repository](https://github.com/microsoft/table-transformer). 
+
+Disclaimer: The team releasing Table Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.
+
+## Model description
+
+The Table Transformer is equivalent to [DETR](https://huggingface.co/docs/transformers/model_doc/detr), a Transformer-based object detection model. Note that the authors decided to use the "normalize before" setting of DETR, which means that layernorm is applied before self- and cross-attention.
+
+## Usage
+
+You can use the raw model for detecting the structure (like rows, columns) in tables. See the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/table-transformer) for more info.

config.json

@@ -0,0 +1,59 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "TableTransformerForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet18",
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "ce_loss_coefficient": 1,
+  "class_cost": 1,
+  "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": 0.4,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "table",
+    "1": "table column",
+    "2": "table row",
+    "3": "table column header",
+    "4": "table projected row header",
+    "5": "table spanning cell"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "table": 0,
+    "table column": 1,
+    "table column header": 3,
+    "table projected row header": 4,
+    "table row": 2,
+    "table spanning cell": 5
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "table-transformer",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 125,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0.dev0",
+  "use_pretrained_backbone": true
+}

preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "DetrFeatureExtractor",
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "max_size": 1000,
+  "size": 800
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec887aff5bf24e943a1c090b477e1366b62b6d30c0d9be00759c18f16a688579
+size 115509981

requirements.txt

@@ -0,0 +1 @@
+timm