Training in progress, step 50

config.json

@@ -0,0 +1,124 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": null,
+  "architectures": [
+    "RTDetrV2ForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      3,
+      4,
+      6,
+      3
+    ],
+    "downsample_in_bottleneck": false,
+    "downsample_in_first_stage": false,
+    "embedding_size": 64,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "layer_type": "bottleneck",
+    "model_type": "rt_detr_resnet",
+    "num_channels": 3,
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ]
+  },
+  "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_method": "default",
+  "decoder_n_levels": 3,
+  "decoder_n_points": 4,
+  "decoder_offset_scale": 0.5,
+  "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": "building"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "building": 0
+  },
+  "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_v2",
+  "normalize_before": false,
+  "num_denoising": 100,
+  "num_feature_levels": 3,
+  "num_queries": 300,
+  "positional_encoding_temperature": 10000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "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 sha256:072429b3410c3cd9b146b2ec99bbd72a7970cb2141536da6e551bd43e42356f3
+size 171527460

preprocessor_config.json

@@ -0,0 +1,35 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_annotations": true,
+  "do_convert_rgb": null,
+  "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": "RTDetrImageProcessorFast",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "input_data_format": null,
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_segmentation_masks": null,
+  "return_tensors": null,
+  "size": {
+    "height": 480,
+    "width": 480
+  }
+}

runs/Apr15_11-01-37_GV9QM84/events.out.tfevents.1744707699.GV9QM84.7668.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f946da9c4e422245858fa3c15396860b09a8a10565d19d5782afb69ecb3a98d
+size 7749

runs/Apr15_11-21-31_GV9QM84/events.out.tfevents.1744708894.GV9QM84.6864.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f309728f400c1ecd6b9cb0fbae2fe12163cb3f66f0a021442ba06d53fa9c388
+size 7749

runs/Apr15_11-21-31_GV9QM84/events.out.tfevents.1744709053.GV9QM84.6864.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629107d77b6a6ac89b73dcd4f386828a0198544f67d372039889a0b3b8f8a3f6
+size 1073

runs/Apr22_13-16-51_GV9QM84/events.out.tfevents.1745320623.GV9QM84.28412.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c946dd2996925684732c3bd22b907c3666b30457ebed804cbc8c2568fb7c5dd0
+size 7748

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dc822cace6d5b1fae24376fc723fb968a3cf8d7b9476f097cb2f5a59912fef
+size 5368