Duplicate from sessex/CLIPSeg2

Co-authored-by: Sydney Essex <[email protected]>

.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: CLIPSeg
+emoji: 🦀
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 3.16.2
+app_file: app.py
+pinned: false
+duplicated_from: sessex/CLIPSeg2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,108 @@
+from transformers import CLIPSegProcessor, CLIPSegForImageSegmentation
+import gradio as gr
+from PIL import Image
+import torch
+import matplotlib.pyplot as plt
+import torch
+import numpy as np
+
+processor = CLIPSegProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
+model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined")
+
+
+def process_image(image, prompt):
+    inputs = processor(
+        text=prompt, images=image, padding="max_length", return_tensors="pt"
+    )
+
+    # predict
+    with torch.no_grad():
+        outputs = model(**inputs)
+        preds = outputs.logits
+
+    pred = torch.sigmoid(preds)
+    mat = pred.cpu().numpy()
+    mask = Image.fromarray(np.uint8(mat * 255), "L")
+    mask = mask.convert("RGB")
+    mask = mask.resize(image.size)
+    mask = np.array(mask)[:, :, 0]
+
+    # normalize the mask
+    mask_min = mask.min()
+    mask_max = mask.max()
+    mask = (mask - mask_min) / (mask_max - mask_min)
+    return mask
+
+
+def get_masks(prompts, img, threhsold):
+    prompts = prompts.split(",")
+    masks = []
+    for prompt in prompts:
+        mask = process_image(img, prompt)
+        mask = mask > threhsold
+        masks.append(mask)
+    return masks
+
+
+def extract_image(img, pos_prompts, neg_prompts, threshold):
+    positive_masks = get_masks(pos_prompts, img, threshold)
+    negative_masks = get_masks(neg_prompts, img, threshold)
+
+    # combine masks into one masks, logic OR
+    pos_mask = np.any(np.stack(positive_masks), axis=0)
+    neg_mask = np.any(np.stack(negative_masks), axis=0)
+    final_mask = pos_mask & ~neg_mask
+
+    # extract the final image
+    final_mask = Image.fromarray(final_mask.astype(np.uint8) * 255, "L")
+    inverse_mask = np.invert(final_mask)
+    output_image = Image.new("RGBA", img.size, (0, 0, 0, 0))
+    output_image.paste(img, mask=final_mask)
+
+    return output_image, final_mask, inverse_mask
+
+
+title = "Interactive demo: zero-shot image segmentation with CLIPSeg"
+description = "Demo for using CLIPSeg, a CLIP-based model for zero- and one-shot image segmentation. To use it, simply upload an image and add a text to mask (identify in the image), or use one of the examples below and click 'submit'. Results will show up in a few seconds."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2112.10003'>CLIPSeg: Image Segmentation Using Text and Image Prompts</a> | <a href='https://huggingface.co/docs/transformers/main/en/model_doc/clipseg'>HuggingFace docs</a></p>"
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# CLIPSeg: Image Segmentation Using Text and Image Prompts")
+    gr.Markdown(article)
+    gr.Markdown(description)
+
+    with gr.Row():
+        with gr.Column():
+            input_image = gr.Image(type="pil")
+            positive_prompts = gr.Textbox(
+                label="Please describe what you want to identify (comma separated)"
+            )
+            negative_prompts = gr.Textbox(
+                label="Please describe what you want to ignore (comma separated)"
+            )
+
+            input_slider_T = gr.Slider(
+                minimum=0, maximum=1, value=0.4, label="Threshold"
+            )
+            btn_process = gr.Button(label="Process")
+
+        with gr.Column():
+            output_image = gr.Image(label="Result")
+            output_mask = gr.Image(label="Mask")
+            inverse_mask = gr.Image(label="Inverse")
+
+    btn_process.click(
+        extract_image,
+        inputs=[
+            input_image,
+            positive_prompts,
+            negative_prompts,
+            input_slider_T,
+        ],
+        outputs=[output_image, output_mask, inverse_mask],
+        api_name="mask"
+    )
+
+
+demo.launch()

packages.txt

@@ -0,0 +1 @@
+python3-opencv

requirements.txt

@@ -0,0 +1,3 @@
+git+https://github.com/huggingface/transformers.git
+torch
+opencv-python