Model save

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PekingU/rtdetr_r18vd_coco_o365
+tags:
+- generated_from_trainer
+model-index:
+- name: rtdetr-pill-detector
+  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. -->
+
+# rtdetr-pill-detector
+
+This model is a fine-tuned version of [PekingU/rtdetr_r18vd_coco_o365](https://huggingface.co/PekingU/rtdetr_r18vd_coco_o365) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5969
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 49.1683       | 1.0   | 79   | 34.2370         |
+| 18.6682       | 2.0   | 158  | 11.6126         |
+| 12.7908       | 3.0   | 237  | 6.9794          |
+| 10.8112       | 4.0   | 316  | 5.3765          |
+| 8.4986        | 5.0   | 395  | 4.3265          |
+| 7.0638        | 6.0   | 474  | 3.7277          |
+| 6.9021        | 7.0   | 553  | 3.4731          |
+| 6.5311        | 8.0   | 632  | 2.9624          |
+| 6.5105        | 9.0   | 711  | 3.0513          |
+| 6.2654        | 10.0  | 790  | 2.7852          |
+| 5.9322        | 11.0  | 869  | 2.9419          |
+| 5.2394        | 12.0  | 948  | 2.8256          |
+| 5.7140        | 13.0  | 1027 | 2.7302          |
+| 6.3316        | 14.0  | 1106 | 2.6021          |
+| 5.0378        | 15.0  | 1185 | 2.6694          |
+| 5.2466        | 16.0  | 1264 | 2.6375          |
+| 5.3730        | 17.0  | 1343 | 2.6533          |
+| 4.9664        | 18.0  | 1422 | 2.6242          |
+| 5.2872        | 19.0  | 1501 | 2.6111          |
+| 5.5504        | 20.0  | 1580 | 2.5969          |
+
+
+### Framework versions
+
+- Transformers 5.6.1
+- Pytorch 2.11.0+cu130
+- Datasets 4.8.4
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,136 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": null,
+  "architectures": [
+    "RTDetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      2,
+      2,
+      2,
+      2
+    ],
+    "downsample_in_bottleneck": false,
+    "downsample_in_first_stage": false,
+    "dtype": "float32",
+    "embedding_size": 64,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      64,
+      128,
+      256,
+      512
+    ],
+    "layer_type": "basic",
+    "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"
+    ]
+  },
+  "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": 3,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": true,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encode_proj_layers": [
+    2
+  ],
+  "encoder_activation_function": "gelu",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 1024,
+  "encoder_hidden_dim": 256,
+  "encoder_in_channels": [
+    128,
+    256,
+    512
+  ],
+  "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": 0.5,
+  "id2label": {
+    "0": "pills",
+    "1": "Cipro 500",
+    "2": "Ibuphil 600 mg",
+    "3": "Ibuphil Cold 400-60",
+    "4": "Xyzall 5mg",
+    "5": "blue",
+    "6": "pink",
+    "7": "red",
+    "8": "white"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Cipro 500": 1,
+    "Ibuphil 600 mg": 2,
+    "Ibuphil Cold 400-60": 3,
+    "Xyzall 5mg": 4,
+    "blue": 5,
+    "pills": 0,
+    "pink": 6,
+    "red": 7,
+    "white": 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,
+  "transformers_version": "5.6.1",
+  "use_cache": false,
+  "use_focal_loss": true,
+  "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 sha256:14f14b9adead20e2210f469516f72a6d6c6bae1c64b8c955b1bf2ad880f30bfc
+size 80539488

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "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
+  ],
+  "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 sha256:0b4170760098cff9fafecd65cd7d93f4f8aec7d55ea50c4d43ee5b9443eb8cd1
+size 5265