Update README.md

README.md

@@ -11,7 +11,6 @@ tags:
 - STEM-AI-mtl
 datasets:
 - STEM-AI-mtl/City_map
-
 widget:
 - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
   example_title: Tiger
@@ -19,43 +18,22 @@ widget:
   example_title: Teapot
 - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
   example_title: Palace
+metrics:
+- accuracy
 ---
 
 # The fine-tuned ViT model that beats [Google's base model](https://huggingface.co/google/vit-base-patch16-224) and OpenAI's GPT4
 
-Image-classification model that identifies which city map is illustrated from an image input.
-
-## Model description
-
-The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224.
-
-Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.
+Image-classification fine-tuned model that identifies which city map is illustrated from an image input.
 
-By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.
+The Vision Transformer base model(ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224.
 
 
-### How to use
 
-Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
+### How to use:
 
-```python
-from transformers import ViTImageProcessor, ViTForImageClassification
-from PIL import Image
-import requests
+[Inference script](https://github.com/STEM-ai/Vision/raw/7d92c8daa388eb74e8c336f2d0d3942722fec3c6/ViT_inference.py)
 
-url = 'https://assets.wfcdn.com/im/16661612/compr-r85/4172/41722749/new-york-city-map-on-paper-print.jpg'
-image = Image.open(requests.get(url, stream=True).raw)
-
-processor = ViTImageProcessor.from_pretrained('STEM-AI-mtl/City_map-vit-base-patch16-224')
-model = ViTForImageClassification.from_pretrained('STEM-AI-mtl/City_map-vit-base-patch16-224')
-
-inputs = processor(images=image, return_tensors="pt")
-outputs = model(**inputs)
-logits = outputs.logits
-
-predicted_class_idx = logits.argmax(-1).item()
-print("Predicted class:", model.config.id2label[predicted_class_idx])
-```
 
 For more code examples, we refer to the [documentation](https://huggingface.co/transformers/model_doc/vit.html#).
 
@@ -65,10 +43,13 @@ This [Google's ViT-base-patch16-224](https://huggingface.co/google/vit-base-patc
 
 ## Training procedure
 
+A Transformer training was performed on [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on a 4 Gb Nvidia GTX 1650 GPU.
+
+[Training notebook](https://github.com/STEM-ai/Vision/raw/7d92c8daa388eb74e8c336f2d0d3942722fec3c6/Trainer_ViT.ipynb)
 
 ## Training evaluation results
 
-The quality of the training was evaluated with the training dataset and resulted in the following metrics:\
+The most accurate output model was obtained from a learning rate of 1e-3. The quality of the training was evaluated with the training dataset and resulted in the following metrics:\
 
 {'eval_loss': 1.3691096305847168,\
  'eval_accuracy': 0.6666666666666666,\
@@ -81,4 +62,4 @@ The quality of the training was evaluated with the training dataset and resulted
 ## Model Card Authors
 
 STEM.AI: [email protected]\
-[William Harbec](https://www.linkedin.com/in/william-harbec-56a262248/)
+[William Harbec](https://www.linkedin.com/in/william-harbec-56a262248/)