End of training

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PekingU/rtdetr_v2_r50vd
+tags:
+- generated_from_trainer
+model-index:
+- name: rtdetr-v2-r50-cppe5-finetune-2
+  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-v2-r50-cppe5-finetune-2
+
+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: 11.9610
+- Map: 0.3649
+- Map 50: 0.6413
+- Map 75: 0.3314
+- Map Small: 0.3681
+- Map Medium: 0.3514
+- Map Large: 0.5909
+- Mar 1: 0.315
+- Mar 10: 0.5779
+- Mar 100: 0.6508
+- Mar Small: 0.4932
+- Mar Medium: 0.5762
+- Mar Large: 0.784
+- Map Coverall: 0.5504
+- Mar 100 Coverall: 0.8538
+- Map Face Shield: 0.3497
+- Mar 100 Face Shield: 0.7471
+- Map Gloves: 0.2505
+- Mar 100 Gloves: 0.4915
+- Map Goggles: 0.2357
+- Mar 100 Goggles: 0.5655
+- Map Mask: 0.4385
+- Mar 100 Mask: 0.5961
+
+## 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: 8
+- eval_batch_size: 8
+- 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_steps: 300
+- num_epochs: 5
+
+### 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 Coverall | Mar 100 Coverall | Map Face Shield | Mar 100 Face Shield | Map Gloves | Mar 100 Gloves | Map Goggles | Mar 100 Goggles | Map Mask | Mar 100 Mask |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
+| No log        | 1.0   | 107  | 55.3917         | 0.0232 | 0.0485 | 0.0213 | 0.0       | 0.0062     | 0.0249    | 0.04   | 0.0855 | 0.0943  | 0.0       | 0.0516     | 0.1121    | 0.1087       | 0.3068           | 0.0004          | 0.0519              | 0.0001     | 0.0085         | 0.0         | 0.0277          | 0.0069   | 0.0769       |
+| No log        | 2.0   | 214  | 28.9185         | 0.1144 | 0.2063 | 0.1092 | 0.0122    | 0.0769     | 0.1746    | 0.1466 | 0.267  | 0.2858  | 0.0174    | 0.2233     | 0.5011    | 0.3659       | 0.6144           | 0.0255          | 0.238               | 0.0138     | 0.1277         | 0.0502      | 0.2092          | 0.1164   | 0.2396       |
+| No log        | 3.0   | 321  | 19.5631         | 0.1944 | 0.363  | 0.1809 | 0.1027    | 0.1483     | 0.2848    | 0.2424 | 0.4058 | 0.4504  | 0.2156    | 0.4032     | 0.654     | 0.4834       | 0.6883           | 0.0884          | 0.4747              | 0.0624     | 0.2429         | 0.0624      | 0.3692          | 0.2753   | 0.4769       |
+| No log        | 4.0   | 428  | 15.2810         | 0.2345 | 0.4587 | 0.2098 | 0.1045    | 0.1855     | 0.4544    | 0.2525 | 0.4567 | 0.5091  | 0.2361    | 0.4726     | 0.734     | 0.551        | 0.7279           | 0.1186          | 0.543               | 0.1237     | 0.417          | 0.1106      | 0.3846          | 0.2685   | 0.4729       |
+| 55.6421       | 5.0   | 535  | 14.7773         | 0.2391 | 0.4678 | 0.2144 | 0.0671    | 0.1875     | 0.447     | 0.2633 | 0.4649 | 0.5141  | 0.2299    | 0.4817     | 0.7456    | 0.5519       | 0.7369           | 0.1398          | 0.5443              | 0.114      | 0.3906         | 0.1052      | 0.4262          | 0.2844   | 0.4724       |
+
+
+### Framework versions
+
+- Transformers 4.50.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "PekingU/rtdetr_v2_r50vd",
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": null,
+  "architectures": [
+    "RTDetrV2ForObjectDetection"
+  ],
+  "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_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": "Coverall",
+    "1": "Face_Shield",
+    "2": "Gloves",
+    "3": "Goggles",
+    "4": "Mask"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Coverall": 0,
+    "Face_Shield": 1,
+    "Gloves": 2,
+    "Goggles": 3,
+    "Mask": 4
+  },
+  "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": "4.50.0.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 sha256:39fc01619d86b0aa46ae0981942d0ab85500f02c5662afc0a8d5d01b33cb8e2c
+size 171560340

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
+  }
+}

runs/Mar10_16-04-15_b359c044831e/events.out.tfevents.1741622660.b359c044831e.3076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22a0f817f1c89b83d9488a3057d6afe114c423b4f600d5a9e327413d22cf20c
+size 14668

runs/Mar10_16-04-15_b359c044831e/events.out.tfevents.1741623205.b359c044831e.3076.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8de889fbd286b30c1dd38adeb5f4c94dc38e9bb22f3bd2d8d8d4aa34f682ea
+size 1548

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70eaa74dc024fd4428a98302da9b01fadad4ad997b3464bdc9bb94137c9c97d8
+size 5368