Training in progress, epoch 1

config.json

@@ -0,0 +1,102 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "ConditionalDetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 2,
+  "cls_loss_coefficient": 2,
+  "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,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "road-signs",
+    "1": "bus_stop",
+    "2": "do_not_enter",
+    "3": "do_not_stop",
+    "4": "do_not_turn_l",
+    "5": "do_not_turn_r",
+    "6": "do_not_u_turn",
+    "7": "enter_left_lane",
+    "8": "green_light",
+    "9": "left_right_lane",
+    "10": "no_parking",
+    "11": "parking",
+    "12": "ped_crossing",
+    "13": "ped_zebra_cross",
+    "14": "railway_crossing",
+    "15": "red_light",
+    "16": "stop",
+    "17": "t_intersection_l",
+    "18": "traffic_light",
+    "19": "u_turn",
+    "20": "warning",
+    "21": "yellow_light"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "bus_stop": 1,
+    "do_not_enter": 2,
+    "do_not_stop": 3,
+    "do_not_turn_l": 4,
+    "do_not_turn_r": 5,
+    "do_not_u_turn": 6,
+    "enter_left_lane": 7,
+    "green_light": 8,
+    "left_right_lane": 9,
+    "no_parking": 10,
+    "parking": 11,
+    "ped_crossing": 12,
+    "ped_zebra_cross": 13,
+    "railway_crossing": 14,
+    "red_light": 15,
+    "road-signs": 0,
+    "stop": 16,
+    "t_intersection_l": 17,
+    "traffic_light": 18,
+    "u_turn": 19,
+    "warning": 20,
+    "yellow_light": 21
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "conditional_detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 300,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "transformers_version": "4.56.2",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f739bb95b3d7b431b217f94871f1f04edece3347425b810ec440a6bdd980694b
+size 174097272

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConditionalDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": {
+    "height": 480,
+    "width": 480
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_height": 480,
+    "max_width": 480
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948eeaf26e7a01ff026afb5dd0ca32befbad5ee1845d24fffef760757d5a2c72
+size 5777