Duplicate from SRDdev/Image-Caption

Co-authored-by: Shreyas Dixit <SRDdev@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Image Caption
+emoji: 🏅
+colorFrom: blue
+colorTo: blue
+sdk: gradio
+sdk_version: 3.0.5
+app_file: app.py
+pinned: false
+duplicated_from: SRDdev/Image-Caption
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,39 @@
+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)]
+
+title = "Image Captioning "
+
+interface = gr.Interface(
+        fn=predict,
+        inputs = input,
+        theme="grass",
+        outputs=output,
+        examples = examples,
+        title=title,
+    )
+interface.launch(debug=True)

app2.py

@@ -0,0 +1,50 @@
+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 
+
+def set_example_image(example: list) -> dict:
+    return gr.Image.update(value=example[0])
+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;
+}
+'''
+demo = gr.Blocks(css=css)
+with demo:
+  gr.Markdown('''<h1 id="title">Image Caption 🖼️</h1>''')
+  gr.Markdown('''Made by : Shreyas Dixit''')
+  with gr.Column():
+        input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
+        output = gr.outputs.Textbox(type="auto",label="Captions")
+  btn = gr.Button("Genrate Caption")
+  btn.click(fn=predict, inputs=input, outputs=output)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+torch