Create app.py

app.py

@@ -0,0 +1,53 @@
+import cohere
+import gradio as gr
+from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel
+
+co_client = cohere.Client('29JdDGuDUqPx2jqTkQUtsJqZRIwUoqwPKd2j9CRA')
+
+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]
+    img_caption_text = clean_text(tokenizer.decode(caption_ids))
+    caption_text = creative_caption(img_caption_text)
+    hashtags = caption_hashtags(img_caption_text)
+    return caption_text, hashtags
+
+
+def creative_caption(text):
+    return co_client.generate(prompt=f"Write some trendy instagram captions for the following prompt - {text}")
+
+
+def caption_hashtags(text):
+    return co_client.generate(prompt=f"Write some trendy instagram hashtags for the following prompt - {text}")
+
+
+input_upload = gr.inputs.Image(label="Upload any Image", type='pil', optional=True)
+output = [
+    gr.outputs.Textbox(type="auto", label="Captions"),
+    gr.outputs.Textbox(type="auto", label="Hashtags"),
+]
+
+title = "Image Captioning "
+description = "Made for Linesh"
+interface = gr.Interface(
+
+    fn=predict,
+    description=description,
+    inputs=input_upload,
+    theme="grass",
+    outputs=output,
+    title=title,
+)
+interface.launch(debug=True)