Duplicate from olivierdehaene/git-large-coco

Co-authored-by: Olivier Dehaene <olivierdehaene@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: GIT-Large coco
+emoji: 🔥
+colorFrom: yellow
+colorTo: pink
+sdk: gradio
+sdk_version: 3.15.0
+app_file: app.py
+pinned: false
+duplicated_from: olivierdehaene/git-large-coco
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from transformers import AutoProcessor, AutoTokenizer, AutoImageProcessor, AutoModelForCausalLM, BlipForConditionalGeneration, VisionEncoderDecoderModel
+import torch
+
+torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
+torch.hub.download_url_to_file('https://huggingface.co/datasets/nielsr/textcaps-sample/resolve/main/stop_sign.png', 'stop_sign.png')
+torch.hub.download_url_to_file('https://cdn.openai.com/dall-e-2/demos/text2im/astronaut/horse/photo/0.jpg', 'astronaut.jpg')
+
+git_processor = AutoProcessor.from_pretrained("microsoft/git-large-coco")
+git_model = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+git_model.to(device)
+
+def generate_caption(processor, model, image):
+    inputs = processor(images=image, return_tensors="pt").to(device)
+    generated_ids = model.generate(pixel_values=inputs.pixel_values, max_length=50)
+    generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+   
+    return generated_caption
+
+
+def generate_captions(image):
+    return generate_caption(git_processor, git_model, image)
+
+   
+examples = [["cats.jpg"], ["stop_sign.png"], ["astronaut.jpg"]]
+outputs = [gr.outputs.Textbox(label="Caption generated by GIT-Large coco")]
+
+title = "Interactive demo: GIT-Large coco image captioning"
+description = "GIT-Large coco image captioning"
+article = "<p style='text-align: center'><a href='https://huggingface.co/docs/transformers/main/model_doc/blip' target='_blank'>BLIP docs</a> | <a href='https://huggingface.co/docs/transformers/main/model_doc/git' target='_blank'>GIT docs</a></p>"
+
+interface = gr.Interface(fn=generate_captions, 
+                         inputs=gr.inputs.Image(type="pil"),
+                         outputs=outputs,
+                         examples=examples, 
+                         title=title,
+                         description=description,
+                         article=article, 
+                         enable_queue=True)
+interface.launch(debug=True)

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/huggingface/transformers.git
+torch