Training in progress, step 10

config.json

@@ -0,0 +1,191 @@
+{
+  "_name_or_path": "PekingU/rtdetr_r50vd_coco_o365",
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": null,
+  "architectures": [
+    "RTDetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": null,
+  "backbone_config": {
+    "model_type": "rt_detr_resnet",
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ]
+  },
+  "backbone_kwargs": null,
+  "batch_norm_eps": 1e-05,
+  "box_noise_scale": 1.0,
+  "d_model": 256,
+  "decoder_activation_function": "relu",
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 1024,
+  "decoder_in_channels": [
+    256,
+    256,
+    256
+  ],
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": true,
+  "dropout": 0.0,
+  "encode_proj_layers": [
+    2
+  ],
+  "encoder_activation_function": "gelu",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 1024,
+  "encoder_hidden_dim": 256,
+  "encoder_in_channels": [
+    512,
+    1024,
+    2048
+  ],
+  "encoder_layers": 1,
+  "eos_coefficient": 0.0001,
+  "eval_size": null,
+  "feat_strides": [
+    8,
+    16,
+    32
+  ],
+  "focal_loss_alpha": 0.75,
+  "focal_loss_gamma": 2.0,
+  "freeze_backbone_batch_norms": true,
+  "hidden_expansion": 1.0,
+  "id2label": {
+    "0": "acrid",
+    "1": "ancient wisp",
+    "2": "archer bug",
+    "3": "arhaic wisp",
+    "4": "bison",
+    "5": "boarlit",
+    "6": "bramble",
+    "7": "child",
+    "8": "clay man",
+    "9": "colossus",
+    "10": "crab",
+    "11": "cremator",
+    "12": "direseeker",
+    "13": "elder lemurian",
+    "14": "evolved lemurian",
+    "15": "gilded wurms",
+    "16": "golem",
+    "17": "greater wisp",
+    "18": "gup",
+    "19": "ifrit",
+    "20": "imp",
+    "21": "imp overlord",
+    "22": "jellyfish",
+    "23": "lemurian",
+    "24": "lemurian cavalry",
+    "25": "lunx tribe",
+    "26": "lynx totem",
+    "27": "macrobe",
+    "28": "macrobic predator",
+    "29": "magma worm",
+    "30": "mushrum",
+    "31": "parent",
+    "32": "providence",
+    "33": "purple imp",
+    "34": "sanctuary guard",
+    "35": "scavenger",
+    "36": "spider",
+    "37": "spitter",
+    "38": "swift",
+    "39": "temple guard",
+    "40": "tiny imp",
+    "41": "toxic beast",
+    "42": "trokk",
+    "43": "tuber",
+    "44": "wandering vagrant",
+    "45": "whorl",
+    "46": "wisp",
+    "47": "young vagrant"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "acrid": 0,
+    "ancient wisp": 1,
+    "archer bug": 2,
+    "arhaic wisp": 3,
+    "bison": 4,
+    "boarlit": 5,
+    "bramble": 6,
+    "child": 7,
+    "clay man": 8,
+    "colossus": 9,
+    "crab": 10,
+    "cremator": 11,
+    "direseeker": 12,
+    "elder lemurian": 13,
+    "evolved lemurian": 14,
+    "gilded wurms": 15,
+    "golem": 16,
+    "greater wisp": 17,
+    "gup": 18,
+    "ifrit": 19,
+    "imp": 20,
+    "imp overlord": 21,
+    "jellyfish": 22,
+    "lemurian": 23,
+    "lemurian cavalry": 24,
+    "lunx tribe": 25,
+    "lynx totem": 26,
+    "macrobe": 27,
+    "macrobic predator": 28,
+    "magma worm": 29,
+    "mushrum": 30,
+    "parent": 31,
+    "providence": 32,
+    "purple imp": 33,
+    "sanctuary guard": 34,
+    "scavenger": 35,
+    "spider": 36,
+    "spitter": 37,
+    "swift": 38,
+    "temple guard": 39,
+    "tiny imp": 40,
+    "toxic beast": 41,
+    "trokk": 42,
+    "tuber": 43,
+    "wandering vagrant": 44,
+    "whorl": 45,
+    "wisp": 46,
+    "young vagrant": 47
+  },
+  "label_noise_ratio": 0.5,
+  "layer_norm_eps": 1e-05,
+  "learn_initial_query": false,
+  "matcher_alpha": 0.25,
+  "matcher_bbox_cost": 5.0,
+  "matcher_class_cost": 2.0,
+  "matcher_gamma": 2.0,
+  "matcher_giou_cost": 2.0,
+  "model_type": "rt_detr",
+  "normalize_before": false,
+  "num_denoising": 100,
+  "num_feature_levels": 3,
+  "num_queries": 300,
+  "positional_encoding_temperature": 10000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_focal_loss": true,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false,
+  "weight_loss_bbox": 5.0,
+  "weight_loss_giou": 2.0,
+  "weight_loss_vfl": 1.0,
+  "with_box_refine": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd8a510d79b184ccbc35c5b1da299c39a09a5d5ce05de6b6666fa9ba04a2a99
+size 171912816

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": false,
+  "do_pad": false,
+  "do_rescale": true,
+  "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
+  ],
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 640,
+    "width": 640
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843d7fb95465ac0067f0640eea8bdd0bd2e0f4335a30819058bf9872cee45bdf
+size 5240