Update README.md

README.md

@@ -26,21 +26,36 @@ We refined the model on the dataset with descriptions and movie posters by russi
 - **Repository:** [github.com/slivka83](https://github.com/slivka83/)
 - **Demo [optional]:** [@MPC_project_bot](https://t.me/MPC_project_bot)
 
-# Uses
+# How to use
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+```python
+from transformers import AutoTokenizer, AutoModel
 
-## Direct Use
+tokenizer = AutoTokenizer.from_pretrained("dumperize/movie-picture-captioning")
+feature_extractor = ViTFeatureExtractor.from_pretrained("dumperize/movie-picture-captioning")
+model = VisionEncoderDecoderModel.from_pretrained("dumperize/movie-picture-captioning")
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+max_length = 128
+num_beams = 4
+gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
 
-[More Information Needed]
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-## Out-of-Scope Use
+image_path = 'path/to/image.jpg';
+image = Image.open(image_path)
+image = image.resize([224,224])
+if image.mode != "RGB":
+  image = image.convert(mode="RGB")
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+pixel_values = feature_extractor(images=[image], return_tensors="pt").pixel_values
+pixel_values = pixel_values.to(device)
 
-[More Information Needed]
+output_ids = model.generate(pixel_values, **gen_kwargs)
+
+preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
+print([pred.strip() for pred in preds])
+
+```
 
 # Bias, Risks, and Limitations