Jiyog/kitchen-object-resnet-18

README.md

@@ -0,0 +1,94 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+- f1
+model-index:
+- name: resnet-kitchen-object
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6101118133203695
+    - name: F1
+      type: f1
+      value: 0.6021708939263245
+---
+
+<!-- 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. -->
+
+# resnet-kitchen-object
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2989
+- Accuracy: 0.6101
+- F1: 0.6022
+
+## 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: 0.0003
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 14
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 2.3261        | 1.0   | 224  | 3.1962          | 0.2003   | 0.1597 |
+| 2.0485        | 2.0   | 448  | 2.0192          | 0.2897   | 0.2667 |
+| 1.8855        | 3.0   | 672  | 2.0079          | 0.3359   | 0.3114 |
+| 1.8135        | 4.0   | 896  | 2.4398          | 0.2985   | 0.2768 |
+| 1.7122        | 5.0   | 1120 | 1.7434          | 0.4127   | 0.3893 |
+| 1.5719        | 6.0   | 1344 | 1.7204          | 0.4011   | 0.3928 |
+| 1.4702        | 7.0   | 1568 | 1.5112          | 0.4886   | 0.4830 |
+| 1.3995        | 8.0   | 1792 | 1.4794          | 0.4861   | 0.4804 |
+| 1.2542        | 9.0   | 2016 | 1.6779          | 0.4677   | 0.4694 |
+| 1.1446        | 10.0  | 2240 | 1.3876          | 0.5445   | 0.5359 |
+| 1.0104        | 11.0  | 2464 | 1.3369          | 0.5863   | 0.5782 |
+| 0.8867        | 12.0  | 2688 | 1.2919          | 0.5848   | 0.5821 |
+| 0.738         | 13.0  | 2912 | 1.2914          | 0.6057   | 0.6026 |
+| 0.7641        | 14.0  | 3136 | 1.2989          | 0.6101   | 0.6022 |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "ResNetForImageClassification"
+  ],
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsample_in_bottleneck": false,
+  "downsample_in_first_stage": false,
+  "dtype": "float32",
+  "embedding_size": 64,
+  "hidden_act": "relu",
+  "hidden_sizes": [
+    256,
+    512,
+    1024,
+    2048
+  ],
+  "id2label": {
+    "0": "bowl",
+    "1": "fork",
+    "2": "glass",
+    "3": "knife",
+    "4": "mug",
+    "5": "pan",
+    "6": "plate",
+    "7": "spatula",
+    "8": "spoon",
+    "9": "whisk"
+  },
+  "image_size": 224,
+  "label2id": {
+    "bowl": "0",
+    "fork": "1",
+    "glass": "2",
+    "knife": "3",
+    "mug": "4",
+    "pan": "5",
+    "plate": "6",
+    "spatula": "7",
+    "spoon": "8",
+    "whisk": "9"
+  },
+  "layer_type": "bottleneck",
+  "model_type": "resnet",
+  "num_channels": 3,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "problem_type": "single_label_classification",
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541c9395d1ab1615a8cf8ac583df088ccc8c81d3546d7624ecc756b32ac1bb1d
+size 94368544

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "crop_pct": 0.875,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConvNextImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0bfb2962d99bde82dd0e64aa71db08233ac86ac55c6bba8ea82e5cd4448ede4
+size 5841