upload fine-tuned RT-DETRv2 trashify object detection model

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: 9.6943
+- Map: 0.5019
+- Map 50: 0.6587
+- Map 75: 0.5594
+- Map Small: 0.2
+- Map Medium: 0.1466
+- Map Large: 0.5289
+- Mar 1: 0.5637
+- Mar 10: 0.7214
+- Mar 100: 0.7844
+- Mar Small: 0.4
+- Mar Medium: 0.5023
+- Mar Large: 0.826
+- Map Bin: 0.7483
+- Mar 100 Bin: 0.9
+- Map Hand: 0.5688
+- Mar 100 Hand: 0.8225
+- Map Not Bin: 0.1236
+- Mar 100 Not Bin: 0.6357
+- Map Not Hand: -1.0
+- Mar 100 Not Hand: -1.0
+- Map Not Trash: 0.2696
+- Mar 100 Not Trash: 0.6236
+- Map Trash: 0.668
+- Mar 100 Trash: 0.7912
+- Map Trash Arm: 0.6334
+- Mar 100 Trash Arm: 0.9333
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------:|:-----------:|:--------:|:------------:|:-----------:|:---------------:|:------------:|:----------------:|:-------------:|:-----------------:|:---------:|:-------------:|:-------------:|:-----------------:|
+| 95.4203       | 1.0   | 50   | 36.7632         | 0.0969 | 0.1711 | 0.0953 | 0.0       | 0.0279     | 0.099     | 0.154  | 0.2806 | 0.2876  | 0.0       | 0.1466     | 0.3008    | 0.3025  | 0.5014      | 0.1779   | 0.4696       | 0.0005      | 0.0714          | -1.0         | -1.0             | 0.0045        | 0.1847            | 0.0945    | 0.3319        | 0.0012        | 0.1667            |
+| 34.5234       | 2.0   | 100  | 17.3569         | 0.2897 | 0.4017 | 0.3215 | 0.0       | 0.0752     | 0.299     | 0.3142 | 0.5754 | 0.6584  | 0.0       | 0.2153     | 0.7096    | 0.6262  | 0.8298      | 0.5167   | 0.7873       | 0.0294      | 0.4286          | -1.0         | -1.0             | 0.0495        | 0.4819            | 0.5141    | 0.6894        | 0.0021        | 0.7333            |
+| 21.3497       | 3.0   | 150  | 12.3189         | 0.343  | 0.4639 | 0.3804 | 0.0       | 0.1743     | 0.3651    | 0.4478 | 0.6271 | 0.7397  | 0.0       | 0.4795     | 0.7863    | 0.6933  | 0.8738      | 0.5149   | 0.8304       | 0.0087      | 0.5786          | -1.0         | -1.0             | 0.1921        | 0.5917            | 0.6081    | 0.7637        | 0.0409        | 0.8               |
+| 17.6468       | 4.0   | 200  | 10.5626         | 0.439  | 0.5844 | 0.5068 | 0.0875    | 0.1241     | 0.4618    | 0.5399 | 0.6942 | 0.7454  | 0.35      | 0.5125     | 0.7766    | 0.7371  | 0.8936      | 0.5741   | 0.8284       | 0.0357      | 0.6             | -1.0         | -1.0             | 0.2263        | 0.6167            | 0.6307    | 0.7673        | 0.43          | 0.7667            |
+| 15.7918       | 5.0   | 250  | 10.4776         | 0.4151 | 0.5608 | 0.4545 | 0.175     | 0.1627     | 0.4374    | 0.5173 | 0.6789 | 0.7629  | 0.35      | 0.4608     | 0.8144    | 0.7314  | 0.8986      | 0.4641   | 0.8196       | 0.019       | 0.5643          | -1.0         | -1.0             | 0.2707        | 0.6625            | 0.6599    | 0.7991        | 0.3455        | 0.8333            |
+| 14.5311       | 6.0   | 300  | 10.0502         | 0.4165 | 0.5597 | 0.4713 | 0.12      | 0.1546     | 0.445     | 0.5331 | 0.6857 | 0.7796  | 0.4       | 0.5744     | 0.8083    | 0.7386  | 0.9078      | 0.5779   | 0.8216       | 0.104       | 0.6929          | -1.0         | -1.0             | 0.2396        | 0.6681            | 0.6406    | 0.7876        | 0.1982        | 0.8               |
+| 13.6203       | 7.0   | 350  | 10.0281         | 0.4716 | 0.6439 | 0.5424 | 0.32      | 0.1287     | 0.4936    | 0.52   | 0.6664 | 0.7514  | 0.4       | 0.4966     | 0.7923    | 0.7501  | 0.895       | 0.5492   | 0.8137       | 0.0383      | 0.6071          | -1.0         | -1.0             | 0.2462        | 0.6347            | 0.6563    | 0.7912        | 0.5894        | 0.7667            |
+| 12.792        | 8.0   | 400  | 9.6988          | 0.4694 | 0.63   | 0.5055 | 0.0583    | 0.1478     | 0.4985    | 0.5578 | 0.7228 | 0.7949  | 0.35      | 0.5909     | 0.825     | 0.7629  | 0.9092      | 0.5704   | 0.8186       | 0.0824      | 0.7071          | -1.0         | -1.0             | 0.2587        | 0.6389            | 0.6866    | 0.7956        | 0.4551        | 0.9               |
+| 12.2254       | 9.0   | 450  | 9.6264          | 0.5036 | 0.6662 | 0.5728 | 0.175     | 0.1921     | 0.5289    | 0.5642 | 0.7198 | 0.7858  | 0.35      | 0.5449     | 0.8252    | 0.7532  | 0.9007      | 0.5675   | 0.8275       | 0.0833      | 0.6714          | -1.0         | -1.0             | 0.2822        | 0.6194            | 0.6842    | 0.7956        | 0.6513        | 0.9               |
+| 11.7667       | 10.0  | 500  | 9.6943          | 0.5019 | 0.6587 | 0.5594 | 0.2       | 0.1466     | 0.5289    | 0.5637 | 0.7214 | 0.7844  | 0.4       | 0.5023     | 0.826     | 0.7483  | 0.9         | 0.5688   | 0.8225       | 0.1236      | 0.6357          | -1.0         | -1.0             | 0.2696        | 0.6236            | 0.668     | 0.7912        | 0.6334        | 0.9333            |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,136 @@
+{
+  "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": "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,
+  "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 sha256:70fa906d2fb066b8e213bd86e58a39810f1041cee76dcdf864c9e2a28bb03c04
+size 171576780

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be41a9e2dcd84709f310fa7472af851f19b314be9e5f43e4ae8da5aee22afd95
+size 5368