End of training

README.md

@@ -0,0 +1,134 @@
+---
+license: apache-2.0
+base_model: microsoft/cvt-13-384-22k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: cvt-13-384-22k-finetuned-LeafBack
+  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: 0.948051948051948
+---
+
+<!-- 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. -->
+
+# cvt-13-384-22k-finetuned-LeafBack
+
+This model is a fine-tuned version of [microsoft/cvt-13-384-22k](https://huggingface.co/microsoft/cvt-13-384-22k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1695
+- Accuracy: 0.9481
+
+## 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: 2e-05
+- train_batch_size: 100
+- eval_batch_size: 50
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 60
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 7    | 0.6404          | 0.6623   |
+| No log        | 2.0   | 14   | 0.5304          | 0.7273   |
+| No log        | 3.0   | 21   | 0.4551          | 0.7922   |
+| No log        | 4.0   | 28   | 0.3175          | 0.8571   |
+| No log        | 5.0   | 35   | 0.2922          | 0.8701   |
+| No log        | 6.0   | 42   | 0.2964          | 0.8701   |
+| No log        | 7.0   | 49   | 0.2839          | 0.8701   |
+| No log        | 8.0   | 56   | 0.2930          | 0.8571   |
+| No log        | 9.0   | 63   | 0.2856          | 0.8831   |
+| No log        | 10.0  | 70   | 0.2969          | 0.8831   |
+| No log        | 11.0  | 77   | 0.3002          | 0.8701   |
+| No log        | 12.0  | 84   | 0.2919          | 0.8831   |
+| No log        | 13.0  | 91   | 0.2780          | 0.8961   |
+| No log        | 14.0  | 98   | 0.2733          | 0.8831   |
+| No log        | 15.0  | 105  | 0.2489          | 0.8961   |
+| No log        | 16.0  | 112  | 0.2569          | 0.8961   |
+| No log        | 17.0  | 119  | 0.2371          | 0.9091   |
+| No log        | 18.0  | 126  | 0.2367          | 0.9091   |
+| No log        | 19.0  | 133  | 0.2297          | 0.9091   |
+| No log        | 20.0  | 140  | 0.2170          | 0.9221   |
+| No log        | 21.0  | 147  | 0.2132          | 0.9351   |
+| No log        | 22.0  | 154  | 0.2080          | 0.9351   |
+| No log        | 23.0  | 161  | 0.2010          | 0.9481   |
+| No log        | 24.0  | 168  | 0.2106          | 0.9221   |
+| No log        | 25.0  | 175  | 0.2055          | 0.9351   |
+| No log        | 26.0  | 182  | 0.1982          | 0.9481   |
+| No log        | 27.0  | 189  | 0.2105          | 0.9351   |
+| No log        | 28.0  | 196  | 0.2204          | 0.9351   |
+| No log        | 29.0  | 203  | 0.2095          | 0.9351   |
+| No log        | 30.0  | 210  | 0.2107          | 0.9221   |
+| No log        | 31.0  | 217  | 0.1808          | 0.9221   |
+| No log        | 32.0  | 224  | 0.1711          | 0.9351   |
+| No log        | 33.0  | 231  | 0.1777          | 0.9351   |
+| No log        | 34.0  | 238  | 0.1700          | 0.9351   |
+| No log        | 35.0  | 245  | 0.1743          | 0.9221   |
+| No log        | 36.0  | 252  | 0.1877          | 0.9481   |
+| No log        | 37.0  | 259  | 0.1855          | 0.9481   |
+| No log        | 38.0  | 266  | 0.1792          | 0.9481   |
+| No log        | 39.0  | 273  | 0.1607          | 0.9481   |
+| No log        | 40.0  | 280  | 0.1681          | 0.9481   |
+| No log        | 41.0  | 287  | 0.1768          | 0.9481   |
+| No log        | 42.0  | 294  | 0.1909          | 0.9481   |
+| No log        | 43.0  | 301  | 0.1812          | 0.9481   |
+| No log        | 44.0  | 308  | 0.1822          | 0.9481   |
+| No log        | 45.0  | 315  | 0.1731          | 0.9481   |
+| No log        | 46.0  | 322  | 0.1846          | 0.9351   |
+| No log        | 47.0  | 329  | 0.1846          | 0.9481   |
+| No log        | 48.0  | 336  | 0.1915          | 0.9351   |
+| No log        | 49.0  | 343  | 0.1879          | 0.9351   |
+| No log        | 50.0  | 350  | 0.1860          | 0.9351   |
+| No log        | 51.0  | 357  | 0.1907          | 0.9351   |
+| No log        | 52.0  | 364  | 0.1729          | 0.9481   |
+| No log        | 53.0  | 371  | 0.1837          | 0.9351   |
+| No log        | 54.0  | 378  | 0.1793          | 0.9351   |
+| No log        | 55.0  | 385  | 0.1783          | 0.9481   |
+| No log        | 56.0  | 392  | 0.1844          | 0.9351   |
+| No log        | 57.0  | 399  | 0.1724          | 0.9351   |
+| No log        | 58.0  | 406  | 0.1819          | 0.9351   |
+| No log        | 59.0  | 413  | 0.1792          | 0.9351   |
+| No log        | 60.0  | 420  | 0.1695          | 0.9481   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 1.10.0+cu111
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,118 @@
+{
+  "_name_or_path": "microsoft/cvt-13-384-22k",
+  "architectures": [
+    "CvtForImageClassification"
+  ],
+  "attention_drop_rate": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "cls_token": [
+    false,
+    false,
+    true
+  ],
+  "depth": [
+    1,
+    2,
+    10
+  ],
+  "drop_path_rate": [
+    0.0,
+    0.0,
+    0.1
+  ],
+  "drop_rate": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "embed_dim": [
+    64,
+    192,
+    384
+  ],
+  "id2label": {
+    "0": "leafmold",
+    "1": "powdery"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "kernel_qkv": [
+    3,
+    3,
+    3
+  ],
+  "label2id": {
+    "leafmold": 0,
+    "powdery": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "mlp_ratio": [
+    4.0,
+    4.0,
+    4.0
+  ],
+  "model_type": "cvt",
+  "num_channels": 3,
+  "num_heads": [
+    1,
+    3,
+    6
+  ],
+  "num_stages": 3,
+  "padding_kv": [
+    1,
+    1,
+    1
+  ],
+  "padding_q": [
+    1,
+    1,
+    1
+  ],
+  "patch_padding": [
+    2,
+    1,
+    1
+  ],
+  "patch_sizes": [
+    7,
+    3,
+    3
+  ],
+  "patch_stride": [
+    4,
+    2,
+    2
+  ],
+  "pos_embed": [
+    false,
+    false,
+    false
+  ],
+  "problem_type": "single_label_classification",
+  "qkv_bias": [
+    true,
+    true,
+    true
+  ],
+  "qkv_projection_method": [
+    "dw_bn",
+    "dw_bn",
+    "dw_bn"
+  ],
+  "stride_kv": [
+    2,
+    2,
+    2
+  ],
+  "stride_q": [
+    1,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865c08f646c0f338914011f390119b8fcf42eaf8e00fcf49c0ffc7c8c866e790
+size 78629584

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67438c3d06ce8a1877c21e0e3ceb4a6fe7f7d7f28043fde33e8c634a8960e0b0
+size 4399