fine-tuned DETR on loc_beyond_words

config.json

@@ -0,0 +1,87 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone_config": {
+    "backbone": "resnet50",
+    "dtype": "float32",
+    "features_only": true,
+    "freeze_batch_norm_2d": false,
+    "model_type": "timm_backbone",
+    "num_channels": 3,
+    "out_features": [
+      "layer1",
+      "layer2",
+      "layer3",
+      "layer4"
+    ],
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ],
+    "output_stride": null,
+    "stage_names": [
+      "act1",
+      "layer1",
+      "layer2",
+      "layer3",
+      "layer4"
+    ],
+    "use_pretrained_backbone": false
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "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,
+  "dtype": "float32",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "Photograph",
+    "1": "Illustration",
+    "2": "Map",
+    "3": "Comics/Cartoon",
+    "4": "Editorial Cartoon",
+    "5": "Headline",
+    "6": "Advertisement"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Advertisement": 6,
+    "Comics/Cartoon": 3,
+    "Editorial Cartoon": 4,
+    "Headline": 5,
+    "Illustration": 1,
+    "Map": 2,
+    "Photograph": 0
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_queries": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "transformers_version": "5.14.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c8eda6d400c953831d35f5c2c1d95fbc10bf5933150bcf16923c072f2571a16
+size 166500992

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_rescale_deprecated": false,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 800,
+    "shortest_edge": 560
+  }
+}