Update app.py

app.py

@@ -1,44 +1,36 @@
-import torch 
-import re 
-import gradio as gr
-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 
-
-
-
-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 🖼️"
-
-article = "Created By : Shreyas Dixit "
-
-interface = gr.Interface(
-        fn=predict,
-        inputs = input,
-        theme="grass",
-        outputs=output,
-        examples = examples,
-        title=title,
-        description=description,
-        article = article,
-    )
-interface.launch(debug=True)
+
+from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
+
+model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+
+
+max_length = 16
+num_beams = 4
+gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
+
+def predict_step(image_paths):
+  images = []
+  for image_path in image_paths:
+    i_image = Image.open(image_path)
+    if i_image.mode != "RGB":
+      i_image = i_image.convert(mode="RGB")
+
+    images.append(i_image)
+
+  pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
+  pixel_values = pixel_values.to(device)
+
+  output_ids = model.generate(pixel_values, **gen_kwargs)
+
+  preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
+  preds = [pred.strip() for pred in preds]
+  return preds
+
+
+predict_step(['doctor.e16ba4e4.jpg'] # ['a woman in a hospital bed with a woman in a hospital bed']