upload trashify object detection model with data augmentation

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: microsoft/conditional-detr-resnet-50
+tags:
+- generated_from_trainer
+model-index:
+- name: detr_finetuned_trashify_box_detector_with_data_aug
+  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_trashify_box_detector_with_data_aug
+
+This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0749
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 25
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 36.0329       | 1.0   | 50   | 3.4510          |
+| 2.8564        | 2.0   | 100  | 2.2827          |
+| 2.3323        | 3.0   | 150  | 2.1028          |
+| 2.1202        | 4.0   | 200  | 1.8915          |
+| 1.9452        | 5.0   | 250  | 1.6696          |
+| 1.7582        | 6.0   | 300  | 1.5181          |
+| 1.6291        | 7.0   | 350  | 1.4310          |
+| 1.5394        | 8.0   | 400  | 1.3669          |
+| 1.4751        | 9.0   | 450  | 1.3164          |
+| 1.3906        | 10.0  | 500  | 1.2860          |
+| 1.394         | 11.0  | 550  | 1.2915          |
+| 1.338         | 12.0  | 600  | 1.2461          |
+| 1.3071        | 13.0  | 650  | 1.2300          |
+| 1.2772        | 14.0  | 700  | 1.2059          |
+| 1.2363        | 15.0  | 750  | 1.1639          |
+| 1.2213        | 16.0  | 800  | 1.1547          |
+| 1.1372        | 17.0  | 850  | 1.1213          |
+| 1.1423        | 18.0  | 900  | 1.1322          |
+| 1.0991        | 19.0  | 950  | 1.1069          |
+| 1.1041        | 20.0  | 1000 | 1.1001          |
+| 1.0921        | 21.0  | 1050 | 1.0869          |
+| 1.063         | 22.0  | 1100 | 1.0760          |
+| 1.0561        | 23.0  | 1150 | 1.0775          |
+| 1.0373        | 24.0  | 1200 | 1.0799          |
+| 1.0325        | 25.0  | 1250 | 1.0749          |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "microsoft/conditional-detr-resnet-50",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "ConditionalDetrForObjectDetection"
+  ],
+  "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": 2,
+  "cls_loss_coefficient": 2,
+  "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,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "bin",
+    "1": "hand",
+    "2": "not_bin",
+    "3": "not_hand",
+    "4": "not_trash",
+    "5": "trash",
+    "6": "trash_arm"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "bin": 0,
+    "hand": 1,
+    "not_bin": 2,
+    "not_hand": 3,
+    "not_trash": 4,
+    "trash": 5,
+    "trash_arm": 6
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "conditional_detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 300,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.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:fe0684c55e44bd02e61048c6a12912d159e5370547f518c354fcae901301532e
+size 174081852

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_annotations": true,
+  "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": "ConditionalDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 640,
+    "shortest_edge": 640
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66c68bea1d5455cab041a87da03b15d66801c6130700b0c1ebd0179639024df
+size 5240