End of training

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+base_model: facebook/detr-resnet-50
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: '20240704'
+  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. -->
+
+# 20240704
+
+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: 0.2392
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.4262        | 32.0  | 800   | 0.3110          |
+| 0.3444        | 64.0  | 1600  | 0.2795          |
+| 0.3122        | 96.0  | 2400  | 0.2704          |
+| 0.2893        | 128.0 | 3200  | 0.2639          |
+| 0.2823        | 160.0 | 4000  | 0.2518          |
+| 0.2679        | 192.0 | 4800  | 0.2502          |
+| 0.2491        | 224.0 | 5600  | 0.2444          |
+| 0.2354        | 256.0 | 6400  | 0.2495          |
+| 0.2284        | 288.0 | 7200  | 0.2406          |
+| 0.2318        | 320.0 | 8000  | 0.2453          |
+| 0.217         | 352.0 | 8800  | 0.2432          |
+| 0.2124        | 384.0 | 9600  | 0.2469          |
+| 0.2097        | 416.0 | 10400 | 0.2516          |
+| 0.1998        | 448.0 | 11200 | 0.2428          |
+| 0.1944        | 480.0 | 12000 | 0.2445          |
+| 0.1909        | 512.0 | 12800 | 0.2468          |
+| 0.1952        | 544.0 | 13600 | 0.2401          |
+| 0.1903        | 576.0 | 14400 | 0.2408          |
+| 0.1867        | 608.0 | 15200 | 0.2478          |
+| 0.1845        | 640.0 | 16000 | 0.2443          |
+| 0.179         | 672.0 | 16800 | 0.2432          |
+| 0.1744        | 704.0 | 17600 | 0.2410          |
+| 0.1747        | 736.0 | 18400 | 0.2432          |
+| 0.1674        | 768.0 | 19200 | 0.2386          |
+| 0.166         | 800.0 | 20000 | 0.2384          |
+| 0.1686        | 832.0 | 20800 | 0.2399          |
+| 0.1647        | 864.0 | 21600 | 0.2391          |
+| 0.1599        | 896.0 | 22400 | 0.2398          |
+| 0.1633        | 928.0 | 23200 | 0.2401          |
+| 0.1654        | 960.0 | 24000 | 0.2397          |
+| 0.1632        | 992.0 | 24800 | 0.2392          |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.3.0
+- Datasets 2.12.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,159 @@
+{
+  "_name_or_path": "facebook/detr-resnet-50",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": null,
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      3,
+      4,
+      6,
+      3
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "downsample_in_bottleneck": false,
+    "downsample_in_first_stage": false,
+    "early_stopping": false,
+    "embedding_size": 64,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_type": "bottleneck",
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "resnet",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage4"
+    ],
+    "out_indices": [
+      4
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": null,
+  "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": "back mirror",
+    "1": "backseat",
+    "2": "center console",
+    "3": "dashboard",
+    "4": "door front left",
+    "5": "door front right",
+    "6": "driving wheel",
+    "7": "window front left",
+    "8": "window front right"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "back mirror": 0,
+    "backseat": 1,
+    "center console": 2,
+    "dashboard": 3,
+    "door front left": 4,
+    "door front right": 5,
+    "driving wheel": 6,
+    "window front left": 7,
+    "window front right": 8
+  },
+  "mask_loss_coefficient": 1,
+  "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": "4.37.2",
+  "use_pretrained_backbone": null,
+  "use_timm_backbone": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05afe86daabef991adba70b863bc73fa8485934af806b0c86d33a5c97b56fd7
+size 166511952

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "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": "DetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18169e3d21d3de359e74b82472d97c464a93543e97e8ec58b96978778991f05
+size 4728