first commit

config.json

@@ -1,20 +1,49 @@
 {
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "Swinv2ForImageClassification"
+    "TableTransformerForObjectDetection"
   ],
-  "attention_probs_dropout_prob": 0.0,
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": null,
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "ResNetForImageClassification"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
     "depths": [
       2,
       2,
-    6,
+      2,
       2
     ],
-  "drop_path_rate": 0.1,
-  "embed_dim": 96,
-  "encoder_stride": 32,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "downsample_in_bottleneck": false,
+    "downsample_in_first_stage": false,
+    "early_stopping": false,
+    "embedding_size": 64,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      64,
+      128,
+      256,
+      512
+    ],
     "id2label": {
       "0": "tench, Tinca tinca",
       "1": "goldfish, Carassius auratus",
@@ -1017,8 +1046,8 @@
       "998": "ear, spike, capitulum",
       "999": "toilet tissue, toilet paper, bathroom tissue"
     },
-  "image_size": 256,
-  "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
     "label2id": {
       "Afghan hound, Afghan": 160,
       "African chameleon, Chamaeleo chamaeleon": 47,
@@ -2020,28 +2049,107 @@
       "zebra": 340,
       "zucchini, courgette": 939
     },
-  "layer_norm_eps": 1e-05,
-  "mlp_ratio": 4.0,
-  "model_type": "swinv2",
+    "layer_type": "basic",
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "resnet",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
     "num_channels": 3,
-  "num_heads": [
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      1,
+      2,
       3,
-    6,
-    12,
-    24
+      4
     ],
-  "num_layers": 4,
-  "patch_size": 4,
-  "path_norm": true,
-  "pretrained_window_sizes": [
-    0,
-    0,
-    0,
-    0
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
     ],
-  "qkv_bias": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
     "torch_dtype": "float32",
-  "transformers_version": "4.21.0.dev0",
-  "use_absolute_embeddings": false,
-  "window_size": 8
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "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": null,
+  "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,
+  "model_type": "table-transformer",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 125,
+  "position_embedding_type": "sine",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "use_pretrained_backbone": null,
+  "use_timm_backbone": false
 }

preprocessor_config.json

@@ -1,17 +1,23 @@
 {
   "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
   "do_resize": true,
-  "feature_extractor_type": "ViTFeatureExtractor",
+  "format": "coco_detection",
   "image_mean": [
     0.485,
     0.456,
     0.406
   ],
+  "image_processor_type": "DetrImageProcessor",
   "image_std": [
     0.229,
     0.224,
     0.225
   ],
-  "resample": 3,
-  "size": 256
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 800
+  }
 }