Duplicate from ybelkada/blip-image-captioning-space

Co-authored-by: Younes Belkada <ybelkada@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 +1,14 @@
+---
+title: Blip Image Captioning Space
+emoji: 🐨
+colorFrom: purple
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.14.0
+app_file: app.py
+pinned: false
+license: bsd-3-clause
+duplicated_from: ybelkada/blip-image-captioning-space
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import torch
+
+from transformers import BlipForConditionalGeneration, BlipProcessor
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model_image_captioning = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+def inference(raw_image, question, decoding_strategy):    
+    inputs = processor(images=raw_image, text=question, return_tensors="pt")
+
+    if decoding_strategy == "Beam search":
+        inputs["max_length"] = 20
+        inputs["num_beams"] = 5
+    elif decoding_strategy == "Nucleus sampling":
+        inputs["max_length"] = 20
+        inputs["num_beams"] = 1
+        inputs["do_sample"] = True
+        inputs["top_k"] = 50
+        inputs["top_p"] = 0.95
+
+    out = model_image_captioning.generate(**inputs)
+    return processor.batch_decode(out, skip_special_tokens=True)[0]
+
+inputs = [
+        gr.inputs.Image(type='pil'),
+        gr.inputs.Textbox(lines=2, label="Context (optional)"),
+        gr.inputs.Radio(choices=['Beam search','Nucleus sampling'], type="value", default="Nucleus sampling", label="Caption Decoding Strategy")
+    ]
+outputs = gr.outputs.Textbox(label="Output")
+
+title = "BLIP"
+
+description = "Gradio demo for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (Salesforce Research). To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
+
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2201.12086' target='_blank'>BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation</a> | <a href='https://github.com/salesforce/BLIP' target='_blank'>Github Repo</a></p>"
+
+gr.Interface(inference, inputs, outputs, title=title, description=description, article=article).launch(enable_queue=True)

requirements.txt

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