anastasispk/law-game-rt-detr

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: PekingU/rtdetr_r50vd_coco_o365
+tags:
+- generated_from_trainer
+model-index:
+- name: law-game-evidence-replacement-finetune
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# law-game-evidence-replacement-finetune
+
+This model is a fine-tuned version of [PekingU/rtdetr_r50vd_coco_o365](https://huggingface.co/PekingU/rtdetr_r50vd_coco_o365) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 3.4253
+- eval_map: 0.8264
+- eval_map_50: 0.8488
+- eval_map_75: 0.8441
+- eval_map_small: 0.5688
+- eval_map_medium: 0.9527
+- eval_map_large: 0.8547
+- eval_mar_1: 0.7043
+- eval_mar_10: 0.9575
+- eval_mar_100: 0.9727
+- eval_mar_small: 0.5949
+- eval_mar_medium: 0.9738
+- eval_mar_large: 0.9894
+- eval_map_evidence: -1.0
+- eval_mar_100_evidence: -1.0
+- eval_map_ambulance: 0.9802
+- eval_mar_100_ambulance: 0.9899
+- eval_map_artificial_target: 0.9267
+- eval_mar_100_artificial_target: 0.9572
+- eval_map_cartridge: 0.9742
+- eval_mar_100_cartridge: 0.9949
+- eval_map_gun: 0.9165
+- eval_mar_100_gun: 0.9403
+- eval_map_knife: 0.8599
+- eval_mar_100_knife: 0.931
+- eval_map_police: 0.9935
+- eval_mar_100_police: 0.9959
+- eval_map_traffic: 0.9586
+- eval_mar_100_traffic: 0.9726
+- eval_map_traffic_cone: 0.0013
+- eval_mar_100_traffic_cone: 1.0
+- eval_runtime: 50.5267
+- eval_samples_per_second: 16.467
+- eval_steps_per_second: 2.058
+- epoch: 28.0
+- step: 5152
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 50
+
+### Framework versions
+
+- Transformers 4.44.0.dev0
+- Pytorch 2.3.1+cu121
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,112 @@
+{
+  "_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,
+  "hidden_expansion": 1.0,
+  "id2label": {
+    "0": "evidence",
+    "1": "ambulance",
+    "2": "artificial_target",
+    "3": "cartridge",
+    "4": "gun",
+    "5": "knife",
+    "6": "police",
+    "7": "traffic",
+    "8": "traffic_cone"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "ambulance": 1,
+    "artificial_target": 2,
+    "cartridge": 3,
+    "evidence": 0,
+    "gun": 4,
+    "knife": 5,
+    "police": 6,
+    "traffic": 7,
+    "traffic_cone": 8
+  },
+  "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": "4.44.0.dev0",
+  "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 sha256:8cbec5cda1ddefe8f9daaeba676ff68063648b0b7c9e9ab38aa67a7c63dc5df0
+size 171592228

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": "RTDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 480,
+    "width": 480
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8555611b571efdf412a9dedc609daeb79ad133b76bc2cda49e7cc6eefce53577
+size 5240