Model save

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: facebook/detr-resnet-50
+tags:
+- generated_from_trainer
+model-index:
+- name: detr-finetuned-cppe-5-10k-steps
+  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. -->
+
+# detr-finetuned-cppe-5-10k-steps
+
+This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0867
+- Map: 0.0493
+- Map 50: 0.1064
+- Map 75: 0.0379
+- Map Small: 0.0072
+- Map Medium: 0.0304
+- Map Large: 0.0574
+- Mar 1: 0.0805
+- Mar 10: 0.1667
+- Mar 100: 0.2069
+- Mar Small: 0.073
+- Mar Medium: 0.1572
+- Mar Large: 0.2325
+- Map Coverall: 0.1978
+- Mar 100 Coverall: 0.5874
+- Map Face Shield: 0.0
+- Mar 100 Face Shield: 0.0
+- Map Gloves: 0.0253
+- Mar 100 Gloves: 0.204
+- Map Goggles: 0.0
+- Mar 100 Goggles: 0.0
+- Map Mask: 0.0236
+- Mar 100 Mask: 0.2431
+
+## 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: 8
+- seed: 1337
+- 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
+- num_epochs: 2.0
+- 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 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
+| 2.5499        | 1.0   | 213  | 2.3248          | 0.0367 | 0.0798 | 0.0325 | 0.0018    | 0.0114     | 0.0417    | 0.0555 | 0.1278 | 0.1648  | 0.0416    | 0.1044     | 0.2026    | 0.1697       | 0.5104           | 0.0             | 0.0                 | 0.0078     | 0.1813         | 0.0         | 0.0             | 0.0058   | 0.1324       |
+| 2.1119        | 2.0   | 426  | 2.0867          | 0.0493 | 0.1064 | 0.0379 | 0.0072    | 0.0304     | 0.0574    | 0.0805 | 0.1667 | 0.2069  | 0.073     | 0.1572     | 0.2325    | 0.1978       | 0.5874           | 0.0             | 0.0                 | 0.0253     | 0.204          | 0.0         | 0.0             | 0.0236   | 0.2431       |
+
+
+### Framework versions
+
+- Transformers 4.52.0.dev0
+- Pytorch 2.7.0+cu118
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,68 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "Coverall",
+    "1": "Face_Shield",
+    "2": "Gloves",
+    "3": "Goggles",
+    "4": "Mask"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Coverall": 0,
+    "Face_Shield": 1,
+    "Gloves": 2,
+    "Goggles": 3,
+    "Mask": 4
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.0.dev0",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe86aa57b1bae988d030f9f14247795b8d09338f8e2a519d48517f8da385f3d1
+size 166498936

preprocessor_config.json

@@ -0,0 +1,38 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_annotations": true,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetrImageProcessorFast",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "input_data_format": null,
+  "pad_size": {
+    "height": 600,
+    "width": 600
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_segmentation_masks": null,
+  "return_tensors": null,
+  "size": {
+    "max_height": 600,
+    "max_width": 600
+  }
+}

runs/May08_17-24-01_PRLNB25003/events.out.tfevents.1746696262.PRLNB25003.23296.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003d1db6717faf08baa723427384d8484a6e08b855be24454351187b579ca101
+size 9597

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f0c807b775f352694366faef821c2692a89d6e6873b26f3dcfb2e9d77eec99
+size 5841