upload finetuned RT-DETRv2 model on trashify dataset from learn HF course

README.md

@@ -0,0 +1,95 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PekingU/rtdetr_v2_r50vd
+tags:
+- generated_from_trainer
+model-index:
+- name: rt_detrv2_finetuned_trashify_box_detector_v1
+  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. -->
+
+# rt_detrv2_finetuned_trashify_box_detector_v1
+
+This model is a fine-tuned version of [PekingU/rtdetr_v2_r50vd](https://huggingface.co/PekingU/rtdetr_v2_r50vd) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 9.1241
+- Map: 0.43
+- Map 50: 0.5696
+- Map 75: 0.504
+- Map Small: 0.0
+- Map Medium: 0.2939
+- Map Large: 0.4379
+- Mar 1: 0.4831
+- Mar 10: 0.6683
+- Mar 100: 0.7138
+- Mar Small: 0.0
+- Mar Medium: 0.4396
+- Mar Large: 0.7408
+- Map Bin: 0.7822
+- Mar 100 Bin: 0.8782
+- Map Hand: 0.5503
+- Mar 100 Hand: 0.8237
+- Map Not Bin: 0.1143
+- Mar 100 Not Bin: 0.5273
+- Map Not Hand: 0.0108
+- Mar 100 Not Hand: 0.5333
+- Map Not Trash: 0.1591
+- Mar 100 Not Trash: 0.5754
+- Map Trash: 0.6508
+- Mar 100 Trash: 0.8157
+- Map Trash Arm: 0.7426
+- Mar 100 Trash Arm: 0.8429
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- 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: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Map    | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1  | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Bin | Mar 100 Bin | Map Hand | Mar 100 Hand | Map Not Bin | Mar 100 Not Bin | Map Not Hand | Mar 100 Not Hand | Map Not Trash | Mar 100 Not Trash | Map Trash | Mar 100 Trash | Map Trash Arm | Mar 100 Trash Arm |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------:|:-----------:|:--------:|:------------:|:-----------:|:---------------:|:------------:|:----------------:|:-------------:|:-----------------:|:---------:|:-------------:|:-------------:|:-----------------:|
+| 49.9733       | 1.0   | 99   | 12.0835         | 0.3203 | 0.4674 | 0.3424 | 0.0179    | 0.2661     | 0.3322    | 0.34   | 0.5944 | 0.6611  | 0.25      | 0.5244     | 0.6918    | 0.6474  | 0.8574      | 0.5238   | 0.7461       | 0.0675      | 0.6143          | -1.0         | -1.0             | 0.1027        | 0.5667            | 0.5776    | 0.7487        | 0.0031        | 0.4333            |
+| 19.9634       | 2.0   | 198  | 10.2864         | 0.3655 | 0.5109 | 0.4023 | 0.0543    | 0.2008     | 0.3808    | 0.5006 | 0.6538 | 0.6922  | 0.3       | 0.4903     | 0.7206    | 0.7375  | 0.8574      | 0.5285   | 0.7794       | 0.031       | 0.6             | -1.0         | -1.0             | 0.211         | 0.5333            | 0.6379    | 0.7832        | 0.0471        | 0.6               |
+| 16.8253       | 3.0   | 297  | 9.4256          | 0.5134 | 0.6761 | 0.5972 | 0.0409    | 0.2179     | 0.5291    | 0.5318 | 0.7198 | 0.7612  | 0.4       | 0.6131     | 0.7892    | 0.765   | 0.8589      | 0.5846   | 0.7843       | 0.0951      | 0.6357          | -1.0         | -1.0             | 0.1681        | 0.6569            | 0.6675    | 0.7982        | 0.8           | 0.8333            |
+| 15.0193       | 4.0   | 396  | 9.1095          | 0.4935 | 0.6666 | 0.5785 | 0.0308    | 0.3855     | 0.5203    | 0.5489 | 0.7252 | 0.761   | 0.4       | 0.592      | 0.7932    | 0.7817  | 0.8901      | 0.5777   | 0.8098       | 0.1595      | 0.6786          | -1.0         | -1.0             | 0.2067        | 0.6               | 0.6799    | 0.7876        | 0.5552        | 0.8               |
+| 13.5647       | 5.0   | 495  | 8.8113          | 0.5406 | 0.7204 | 0.6351 | 0.001     | 0.2421     | 0.5689    | 0.5632 | 0.7029 | 0.7424  | 0.4       | 0.4847     | 0.7789    | 0.7958  | 0.8851      | 0.6122   | 0.8225       | 0.1892      | 0.5786          | -1.0         | -1.0             | 0.2743        | 0.6014            | 0.681     | 0.8           | 0.6911        | 0.7667            |
+| 12.3311       | 6.0   | 594  | 8.9757          | 0.5597 | 0.7359 | 0.6413 | 0.0021    | 0.2627     | 0.5877    | 0.5873 | 0.7451 | 0.7768  | 0.35      | 0.5716     | 0.8105    | 0.7933  | 0.8865      | 0.5739   | 0.802        | 0.2277      | 0.6571          | -1.0         | -1.0             | 0.2669        | 0.6278            | 0.6625    | 0.7876        | 0.8338        | 0.9               |
+| 11.3095       | 7.0   | 693  | 9.0993          | 0.5256 | 0.7043 | 0.6096 | 0.0003    | 0.2768     | 0.5546    | 0.5767 | 0.7239 | 0.7611  | 0.3       | 0.5909     | 0.7934    | 0.785   | 0.8752      | 0.588    | 0.7902       | 0.1903      | 0.6643          | -1.0         | -1.0             | 0.2666        | 0.6125            | 0.6586    | 0.7912        | 0.6654        | 0.8333            |
+| 10.3959       | 8.0   | 792  | 9.0847          | 0.5307 | 0.7005 | 0.6144 | 0.0       | 0.351      | 0.5598    | 0.5772 | 0.7106 | 0.7491  | 0.0       | 0.5398     | 0.7868    | 0.8053  | 0.8823      | 0.589    | 0.7873       | 0.1919      | 0.6714          | -1.0         | -1.0             | 0.2452        | 0.5694            | 0.6602    | 0.7841        | 0.6923        | 0.8               |
+| 9.7215        | 9.0   | 891  | 9.2169          | 0.5327 | 0.7083 | 0.6145 | 0.0       | 0.2484     | 0.5644    | 0.5807 | 0.7244 | 0.7496  | 0.0       | 0.5193     | 0.7887    | 0.8121  | 0.8823      | 0.5569   | 0.7471       | 0.1826      | 0.6786          | -1.0         | -1.0             | 0.2546        | 0.5694            | 0.657     | 0.7867        | 0.7327        | 0.8333            |
+| 9.1183        | 10.0  | 990  | 9.2996          | 0.5294 | 0.7099 | 0.6115 | 0.0       | 0.2496     | 0.5584    | 0.582  | 0.7183 | 0.7457  | 0.0       | 0.5199     | 0.7829    | 0.7925  | 0.8745      | 0.5496   | 0.7471       | 0.1949      | 0.6643          | -1.0         | -1.0             | 0.2514        | 0.5694            | 0.6555    | 0.7858        | 0.7327        | 0.8333            |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.9.0+cu126
+- Datasets 4.4.1
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,137 @@
+{
+  "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,
+    "dtype": "float32",
+    "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,
+  "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": [
+    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": "bin",
+    "1": "hand",
+    "2": "not_bin",
+    "3": "not_hand",
+    "4": "not_trash",
+    "5": "trash",
+    "6": "trash_arm"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "bin": 0,
+    "hand": 1,
+    "not_bin": 2,
+    "not_hand": 3,
+    "not_trash": 4,
+    "trash": 5,
+    "trash_arm": 6
+  },
+  "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,
+  "transformers_version": "4.57.1",
+  "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:a60589006da8081a20e2ec35bc3edb08329fa04f6a392cb17493f6a1ca8ef8ae
+size 171576780

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_annotations": true,
+  "do_convert_rgb": null,
+  "do_normalize": false,
+  "do_pad": true,
+  "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": {
+    "longest_edge": 640,
+    "shortest_edge": 640
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089cb1c148dccf4f879f1540aad5fc5f67d32bb8a6cb251eeb46940d5c9f397a
+size 5905