End of training

README.md

@@ -0,0 +1,89 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: facebook/detr-resnet-50
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1423
+
+## 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: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 2    | 5.4207          |
+| No log        | 2.0   | 4    | 3.5959          |
+| No log        | 3.0   | 6    | 2.6546          |
+| No log        | 4.0   | 8    | 2.5924          |
+| 4.7135        | 5.0   | 10   | 2.4246          |
+| 4.7135        | 6.0   | 12   | 2.3156          |
+| 4.7135        | 7.0   | 14   | 2.0630          |
+| 4.7135        | 8.0   | 16   | 1.8700          |
+| 4.7135        | 9.0   | 18   | 1.9057          |
+| 1.9751        | 10.0  | 20   | 1.8555          |
+| 1.9751        | 11.0  | 22   | 1.7879          |
+| 1.9751        | 12.0  | 24   | 1.6941          |
+| 1.9751        | 13.0  | 26   | 1.6313          |
+| 1.9751        | 14.0  | 28   | 1.5788          |
+| 1.6067        | 15.0  | 30   | 1.5095          |
+| 1.6067        | 16.0  | 32   | 1.4926          |
+| 1.6067        | 17.0  | 34   | 1.3962          |
+| 1.6067        | 18.0  | 36   | 1.3799          |
+| 1.6067        | 19.0  | 38   | 1.4024          |
+| 1.3628        | 20.0  | 40   | 1.3731          |
+| 1.3628        | 21.0  | 42   | 1.3351          |
+| 1.3628        | 22.0  | 44   | 1.2939          |
+| 1.3628        | 23.0  | 46   | 1.3056          |
+| 1.3628        | 24.0  | 48   | 1.2118          |
+| 1.2051        | 25.0  | 50   | 1.1925          |
+| 1.2051        | 26.0  | 52   | 1.1810          |
+| 1.2051        | 27.0  | 54   | 1.1621          |
+| 1.2051        | 28.0  | 56   | 1.1491          |
+| 1.2051        | 29.0  | 58   | 1.1433          |
+| 1.0991        | 30.0  | 60   | 1.1423          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,241 @@
+{
+  "_name_or_path": "facebook/detr-resnet-50",
+  "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": "N/A",
+    "1": "person",
+    "2": "bicycle",
+    "3": "car",
+    "4": "motorcycle",
+    "5": "airplane",
+    "6": "bus",
+    "7": "train",
+    "8": "truck",
+    "9": "boat",
+    "10": "traffic light",
+    "11": "fire hydrant",
+    "12": "street sign",
+    "13": "stop sign",
+    "14": "parking meter",
+    "15": "bench",
+    "16": "bird",
+    "17": "cat",
+    "18": "dog",
+    "19": "horse",
+    "20": "sheep",
+    "21": "cow",
+    "22": "elephant",
+    "23": "bear",
+    "24": "zebra",
+    "25": "giraffe",
+    "26": "hat",
+    "27": "backpack",
+    "28": "umbrella",
+    "29": "shoe",
+    "30": "eye glasses",
+    "31": "handbag",
+    "32": "tie",
+    "33": "suitcase",
+    "34": "frisbee",
+    "35": "skis",
+    "36": "snowboard",
+    "37": "sports ball",
+    "38": "kite",
+    "39": "baseball bat",
+    "40": "baseball glove",
+    "41": "skateboard",
+    "42": "surfboard",
+    "43": "tennis racket",
+    "44": "bottle",
+    "45": "plate",
+    "46": "wine glass",
+    "47": "cup",
+    "48": "fork",
+    "49": "knife",
+    "50": "spoon",
+    "51": "bowl",
+    "52": "banana",
+    "53": "apple",
+    "54": "sandwich",
+    "55": "orange",
+    "56": "broccoli",
+    "57": "carrot",
+    "58": "hot dog",
+    "59": "pizza",
+    "60": "donut",
+    "61": "cake",
+    "62": "chair",
+    "63": "couch",
+    "64": "potted plant",
+    "65": "bed",
+    "66": "mirror",
+    "67": "dining table",
+    "68": "window",
+    "69": "desk",
+    "70": "toilet",
+    "71": "door",
+    "72": "tv",
+    "73": "laptop",
+    "74": "mouse",
+    "75": "remote",
+    "76": "keyboard",
+    "77": "cell phone",
+    "78": "microwave",
+    "79": "oven",
+    "80": "toaster",
+    "81": "sink",
+    "82": "refrigerator",
+    "83": "blender",
+    "84": "book",
+    "85": "clock",
+    "86": "vase",
+    "87": "scissors",
+    "88": "teddy bear",
+    "89": "hair drier",
+    "90": "toothbrush"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "N/A": 0,
+    "airplane": 5,
+    "apple": 53,
+    "backpack": 27,
+    "banana": 52,
+    "baseball bat": 39,
+    "baseball glove": 40,
+    "bear": 23,
+    "bed": 65,
+    "bench": 15,
+    "bicycle": 2,
+    "bird": 16,
+    "blender": 83,
+    "boat": 9,
+    "book": 84,
+    "bottle": 44,
+    "bowl": 51,
+    "broccoli": 56,
+    "bus": 6,
+    "cake": 61,
+    "car": 3,
+    "carrot": 57,
+    "cat": 17,
+    "cell phone": 77,
+    "chair": 62,
+    "clock": 85,
+    "couch": 63,
+    "cow": 21,
+    "cup": 47,
+    "desk": 69,
+    "dining table": 67,
+    "dog": 18,
+    "donut": 60,
+    "door": 71,
+    "elephant": 22,
+    "eye glasses": 30,
+    "fire hydrant": 11,
+    "fork": 48,
+    "frisbee": 34,
+    "giraffe": 25,
+    "hair drier": 89,
+    "handbag": 31,
+    "hat": 26,
+    "horse": 19,
+    "hot dog": 58,
+    "keyboard": 76,
+    "kite": 38,
+    "knife": 49,
+    "laptop": 73,
+    "microwave": 78,
+    "mirror": 66,
+    "motorcycle": 4,
+    "mouse": 74,
+    "orange": 55,
+    "oven": 79,
+    "parking meter": 14,
+    "person": 1,
+    "pizza": 59,
+    "plate": 45,
+    "potted plant": 64,
+    "refrigerator": 82,
+    "remote": 75,
+    "sandwich": 54,
+    "scissors": 87,
+    "sheep": 20,
+    "shoe": 29,
+    "sink": 81,
+    "skateboard": 41,
+    "skis": 35,
+    "snowboard": 36,
+    "spoon": 50,
+    "sports ball": 37,
+    "stop sign": 13,
+    "street sign": 12,
+    "suitcase": 33,
+    "surfboard": 42,
+    "teddy bear": 88,
+    "tennis racket": 43,
+    "tie": 32,
+    "toaster": 80,
+    "toilet": 70,
+    "toothbrush": 90,
+    "traffic light": 10,
+    "train": 7,
+    "truck": 8,
+    "tv": 72,
+    "umbrella": 28,
+    "vase": 86,
+    "window": 68,
+    "wine glass": 46,
+    "zebra": 24
+  },
+  "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": "4.44.2",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929aa69b1d934a5f8787997bb6f50977153a042b6a4fe25313bd100dbd749695
+size 166587352

runs/Nov03_14-45-43_3b0b7e9fa300/events.out.tfevents.1730645144.3b0b7e9fa300.361.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadd66b173eee178918d3b452896933c56a992391606c8f806499af5e7544e29
+size 18674

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4850c3b00208195609486ef801ffbac9c1bc9a19c6a8ad6d8335c2e7db0706fd
+size 5176