Spaces:
Runtime error
Runtime error
| import torch | |
| import gradio as gr | |
| import re | |
| from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel | |
| device='cpu' | |
| encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning" | |
| decoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning" | |
| model_checkpoint = "nlpconnect/vit-gpt2-image-captioning" | |
| feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint) | |
| tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint) | |
| model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device) | |
| def predict(image,max_length=64, num_beams=4): | |
| image = image.convert('RGB') | |
| image = feature_extractor(image, return_tensors="pt").pixel_values.to(device) | |
| clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0] | |
| caption_ids = model.generate(image, max_length = max_length)[0] | |
| caption_text = clean_text(tokenizer.decode(caption_ids)) | |
| return caption_text | |
| css = ''' | |
| h1#title { | |
| text-align: center; | |
| } | |
| h3#header { | |
| text-align: center; | |
| } | |
| img#overview { | |
| max-width: 800px; | |
| max-height: 600px; | |
| } | |
| img#style-image { | |
| max-width: 1000px; | |
| max-height: 600px; | |
| } | |
| ''' | |
| input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True) | |
| output = gr.outputs.Textbox(type="auto",label="Captions") | |
| examples = [f"example{i}.jpg" for i in range(1,7)] | |
| description= "Image captioning application made using transformers" | |
| title = "Image Captioning 🖼️" | |
| interface = gr.Interface( | |
| fn=predict, | |
| inputs = input, | |
| theme="grass", | |
| outputs=output, | |
| examples = examples, | |
| title=title, | |
| description=description, | |
| article = article, | |
| ) | |
| interface.launch(debug=True) |