image-classification

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- fungi
+- mushrooms
+- generated_from_trainer
+metrics:
+- accuracy
+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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the cifar10 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0583
+- Accuracy: 0.9865
+
+## 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: 32
+- seed: 42
+- optimizer: Use 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0388        | 1.0   | 1563 | 0.0732          | 0.9815   |
+| 0.017         | 2.0   | 3126 | 0.0621          | 0.9847   |
+| 0.0028        | 3.0   | 4689 | 0.0583          | 0.9865   |
+
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.7.0+cu118
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "airplane",
+    "1": "automobile",
+    "2": "bird",
+    "3": "cat",
+    "4": "deer",
+    "5": "dog",
+    "6": "frog",
+    "7": "horse",
+    "8": "ship",
+    "9": "truck"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "airplane": 0,
+    "automobile": 1,
+    "bird": 2,
+    "cat": 3,
+    "deer": 4,
+    "dog": 5,
+    "frog": 6,
+    "horse": 7,
+    "ship": 8,
+    "truck": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371a0394884285c44720b1c1cc2d90c1597ff4024f94e2d14c32d00507ca2c80
+size 343248584

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a009187eb7124e6ac60b79581355b5c313b448417a5702d904488655912ad78e
+size 5649