update readme

README.md

@@ -9,31 +9,66 @@ metrics:
 - rouge
 - meteor
 - bertscore
-base_model: microsoft/swin-base-patch4-window7-224
+base_model:
+- microsoft/swin-base-patch4-window7-224
 pipeline_tag: text-generation
 ---
 
-# Model Card for Model ID
+# 🎉 Swin-GPorTuguese
 
-<!-- Provide a quick summary of what the model is/does. -->
+Swin-GPorTuguese model trained on [Flickr30K Portuguese](https://huggingface.co/datasets/laicsiifes/flickr30k-pt-br) (translated version using Google Translator API)
+at resolution 224x224 and max sequence length of 1024 tokens.
 
 
-## Model Description
+## 🤖 Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+The Swin-GPorTuguese is a type of Vision Encoder Decoder which leverage the checkpoints of the [Swin Transformer](https://huggingface.co/microsoft/swin-base-patch4-window7-224)
+as encoder and the checkpoints of the [GPorTuguese](pierreguillou/gpt2-small-portuguese) as decoder.
+The encoder checkpoints come from Swin Trasnformer version pre-trained on ImageNet-1k at resolution 224x224.
 
+The code used for training and evaluation is available at: https://github.com/laicsiifes/ved-transformer-caption-ptbr. In this work, Swin-GPorTuguese
+was trained together with its buddy [Swin-DistilBERTimbau](https://huggingface.co/laicsiifes/swin-distilbert-flickr30k-pt-br). 
 
-## How to Get Started with the Model
+Other models evaluated didn't achieve performance as high as Swin-DistilBERTimbau and Swin-GPorTuguese, namely: DeiT-BERTimbau,
+DeiT-DistilBERTimbau, DeiT-GPorTuguese, Swin-BERTimbau, ViT-BERTimbau, ViT-DistilBERTimbau and ViT-GPorTuguese.
+
+## 🧑‍💻 How to Get Started with the Model
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+```python
+import requests
+from PIL import Image
+
+from transformers import AutoTokenizer, ViTImageProcessor, VisionEncoderDecoderModel
+
+# load a fine-tuned image captioning model and corresponding tokenizer and image processor
+model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
+tokenizer = GPT2TokenizerFast.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
+image_processor = ViTImageProcessor.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
+
+# perform inference on an image
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+pixel_values = image_processor(image, return_tensors="pt").pixel_values
+
+# generate caption
+generated_ids = model.generate(pixel_values)
+generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(generated_text)
+```
 
+## 📈 Results
 
-### Results
+The evaluation metrics Cider-D, BLEU@4, ROUGE-L, METEOR and BERTScore are abbreviated as C, B@4, RL, M and BS, respectively.
 
-[More Information Needed]
+|Model|Training|Evaluation|C|B@4|RL|M|BS|
+|-----|--------|----------|-------|------|-------|------|---------|
+|Swin-DistilBERTimbau|Flickr30K Portuguese|Flickr30K Portuguese|66.73|24.65|39.98|44.71|72.30|
+|Swin-GPorTuguese|Flickr30K Portuguese|Flickr30K Portuguese|64.71|23.15|39.39|44.36|71.70|
 
-**BibTeX:**
+## 📋 BibTeX entry and citation info
 
-[More Information Needed]
+```bibtex
+Coming Soon
+```