Initial model upload

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: google/vit-large-patch16-224-in21k
+tags:
+- image-classification
+- vision
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: large
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: citeseerx/ACL-fig
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9281437125748503
+---
+
+<!-- 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. -->
+
+# large
+
+This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the citeseerx/ACL-fig dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2075
+- Accuracy: 0.9281
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 1337
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6973        | 1.0   | 335  | 0.5066          | 0.8563   |
+| 0.2901        | 2.0   | 670  | 0.3553          | 0.8892   |
+| 0.2782        | 3.0   | 1005 | 0.2585          | 0.9162   |
+| 0.1351        | 4.0   | 1340 | 0.2233          | 0.9281   |
+| 0.1683        | 5.0   | 1675 | 0.2075          | 0.9281   |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9281437125748503,
+    "eval_loss": 0.20753857493400574,
+    "eval_runtime": 6.0243,
+    "eval_samples_per_second": 55.442,
+    "eval_steps_per_second": 6.972,
+    "train_loss": 0.41028220598377396,
+    "train_runtime": 581.3967,
+    "train_samples_per_second": 22.988,
+    "train_steps_per_second": 2.881
+}

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "google/vit-large-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Line graph_chart",
+    "1": "NLP text_grammar_eg",
+    "10": "natural images",
+    "11": "neural networks",
+    "12": "pareto",
+    "13": "pie chart",
+    "14": "scatter plot",
+    "15": "tables",
+    "16": "trees",
+    "17": "venn diagram",
+    "18": "word cloud",
+    "2": "Screenshots",
+    "3": "algorithms",
+    "4": "architecture diagram",
+    "5": "bar charts",
+    "6": "boxplots",
+    "7": "confusion matrix",
+    "8": "graph",
+    "9": "maps"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Line graph_chart": "0",
+    "NLP text_grammar_eg": "1",
+    "Screenshots": "2",
+    "algorithms": "3",
+    "architecture diagram": "4",
+    "bar charts": "5",
+    "boxplots": "6",
+    "confusion matrix": "7",
+    "graph": "8",
+    "maps": "9",
+    "natural images": "10",
+    "neural networks": "11",
+    "pareto": "12",
+    "pie chart": "13",
+    "scatter plot": "14",
+    "tables": "15",
+    "trees": "16",
+    "venn diagram": "17",
+    "word cloud": "18"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9281437125748503,
+    "eval_loss": 0.20753857493400574,
+    "eval_runtime": 6.0243,
+    "eval_samples_per_second": 55.442,
+    "eval_steps_per_second": 6.972
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2542a4764767f3733afc3cd723eb9a0abbc1e5872fc73cb128150dac12476999
+size 1213330972

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
+  }
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.41028220598377396,
+    "train_runtime": 581.3967,
+    "train_samples_per_second": 22.988,
+    "train_steps_per_second": 2.881
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec4376a318ed2d793bb1905b111c55e16d7efb9bbe32d01b764579112f54661
+size 4664