app.py

import gradio as gr

from io import BytesIO
import requests
import PIL
from PIL import Image
import numpy as np
import os
import uuid
import torch
from torch import autocast
import cv2
from matplotlib import pyplot as plt
from inpainting import StableDiffusionInpaintingPipeline
from torchvision import transforms
from clipseg.models.clipseg import CLIPDensePredT

#from huggingface_hub import hf_hub_download
#hf_hub_download(repo_id="ThereforeGames/txt2mask", filename="/repositories/clipseg/")
#clone_from (str, optional) — Either a repository url or repo_id. Example:
#api = HfApi()

#from huggingface_hub import Repository
#with Repository(local_dir="clipseg", clone_from="ThereforeGames/txt2mask/repositories/clipseg/")
"""
import sys
import os

from zipfile import ZipFile
zf = ZipFile('clipseg-master.zip', 'r')
zf.extractall('./clipseg')
zf.close()


from huggingface_hub import HfApi
api = HfApi()
api.upload_folder(
    folder_path="/",
    path_in_repo="ThereforeGames/txt2mask/repositories/clipseg/",
    repo_id="ThereforeGames/txt2mask",
#    repo_type="dataset",
#    ignore_patterns="**/logs/*.txt",
)
"""
#.commit(commit_message="clipseg uploaded...")
#    with open("file.txt", "w+") as f:
#        f.write(json.dumps({"hey": 8}))


auth_token = os.environ.get("API_TOKEN") or True

def download_image(url):
    response = requests.get(url)
    return PIL.Image.open(BytesIO(response.content)).convert("RGB")

device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = StableDiffusionInpaintingPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    revision="fp16", 
    torch_dtype=torch.float16 if torch.cuda.is_available() else float
    use_auth_token=auth_token,
).to(device)

model = CLIPDensePredT(version='ViT-B/16', reduce_dim=64)
model.eval()
model.load_state_dict(torch.load('./clipseg/weights/rd64-uni.pth', map_location=torch.device(device)), strict=False)

transform = transforms.Compose([
      transforms.ToTensor(),
      transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
      transforms.Resize((512, 512)),
])

def predict(radio, dict, word_mask, prompt=""):
    if(radio == "draw a mask above"):
        with autocast(device): #"cuda"
            init_image = dict["image"].convert("RGB").resize((512, 512))
            mask = dict["mask"].convert("RGB").resize((512, 512))
    elif(radio == "type what to keep"):
        img = transform(dict["image"]).squeeze(0)
        word_masks = [word_mask]
        with torch.no_grad():
            preds = model(img.repeat(len(word_masks),1,1,1), word_masks)[0]
        init_image = dict['image'].convert('RGB').resize((512, 512))
        filename = f"{uuid.uuid4()}.png"
        plt.imsave(filename,torch.sigmoid(preds[0][0]))
        img2 = cv2.imread(filename)
        gray_image = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
        (thresh, bw_image) = cv2.threshold(gray_image, 100, 255, cv2.THRESH_BINARY)
        cv2.cvtColor(bw_image, cv2.COLOR_BGR2RGB)
        mask = Image.fromarray(np.uint8(bw_image)).convert('RGB')
        os.remove(filename)
    else:
        img = transform(dict["image"]).unsqueeze(0)
        word_masks = [word_mask]
        with torch.no_grad():
            preds = model(img.repeat(len(word_masks),1,1,1), word_masks)[0]
        init_image = dict['image'].convert('RGB').resize((512, 512))
        filename = f"{uuid.uuid4()}.png"
        plt.imsave(filename,torch.sigmoid(preds[0][0]))
        img2 = cv2.imread(filename)
        gray_image = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
        (thresh, bw_image) = cv2.threshold(gray_image, 100, 255, cv2.THRESH_BINARY)
        cv2.cvtColor(bw_image, cv2.COLOR_BGR2RGB)
        mask = Image.fromarray(np.uint8(bw_image)).convert('RGB')
        os.remove(filename)
    with autocast(device): #"cuda"
        images = pipe(prompt = prompt, init_image=init_image, mask_image=mask, strength=0.8)["sample"]
    return images[0]

# examples = [[dict(image="init_image.png", mask="mask_image.png"), "A panda sitting on a bench"]]
css = '''
.container {max-width: 1150px;margin: auto;padding-top: 1.5rem}
#image_upload{min-height:400px}
#image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 400px}
#mask_radio .gr-form{background:transparent; border: none}
#word_mask{margin-top: .75em !important}
#word_mask textarea:disabled{opacity: 0.3}
.footer {margin-bottom: 45px;margin-top: 35px;text-align: center;border-bottom: 1px solid #e5e5e5}
.footer>p {font-size: .8rem; display: inline-block; padding: 0 10px;transform: translateY(10px);background: white}
.dark .footer {border-color: #303030}
.dark .footer>p {background: #0b0f19}
.acknowledgments h4{margin: 1.25em 0 .25em 0;font-weight: bold;font-size: 115%}
#image_upload .touch-none{display: flex}

.markdown-body {
	font-family: -apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif,"Apple Color Emoji","Segoe UI Emoji";
	font-size: 16px;
	line-height: 1.5;
	word-wrap: break-word;
}
.container-lg {
	max-width: 1012px;
	margin-right: auto;
	margin-left: auto;
}
[data-color-mode="auto"][data-light-theme*="light"] {
	--color-workflow-card-connector: var(--color-scale-gray-3);
	--color-workflow-card-connector-bg: var(--color-scale-gray-3);
	--color-workflow-card-connector-inactive: var(--color-border-default);
	--color-workflow-card-connector-inactive-bg: var(--color-border-default);
	--color-workflow-card-connector-highlight: var(--color-scale-blue-4);
	--color-workflow-card-connector-highlight-bg: var(--color-scale-blue-4);
	--color-workflow-card-bg: var(--color-scale-white);
	--color-workflow-card-inactive-bg: var(--color-canvas-inset);
	--color-workflow-card-header-shadow: rgba(0, 0, 0, 0);
	--color-workflow-card-progress-complete-bg: var(--color-scale-blue-4);
	--color-workflow-card-progress-incomplete-bg: var(--color-scale-gray-2);
	--color-discussions-state-answered-icon: var(--color-scale-white);
	--color-bg-discussions-row-emoji-box: rgba(209, 213, 218, 0.5);
	--color-notifications-button-text: var(--color-fg-muted);
	--color-notifications-button-hover-text: var(--color-fg-default);
	--color-notifications-button-hover-bg: var(--color-scale-gray-2);
	--color-notifications-row-read-bg: var(--color-canvas-subtle);
	--color-notifications-row-bg: var(--color-scale-white);
	--color-icon-directory: var(--color-scale-blue-3);
	--color-checks-step-error-icon: var(--color-scale-red-4);
	--color-calendar-halloween-graph-day-L1-bg: #ffee4a;
	--color-calendar-halloween-graph-day-L2-bg: #ffc501;
	--color-calendar-halloween-graph-day-L3-bg: #fe9600;
	--color-calendar-halloween-graph-day-L4-bg: #03001c;
	--color-calendar-graph-day-bg: #ebedf0;
	--color-calendar-graph-day-border: rgba(27, 31, 35, 0.06);
	--color-calendar-graph-day-L1-bg: #9be9a8;
	--color-calendar-graph-day-L2-bg: #40c463;
	--color-calendar-graph-day-L3-bg: #30a14e;
	--color-calendar-graph-day-L4-bg: #216e39;
	--color-calendar-graph-day-L1-border: rgba(27, 31, 35, 0.06);
	--color-calendar-graph-day-L2-border: rgba(27, 31, 35, 0.06);
	--color-calendar-graph-day-L3-border: rgba(27, 31, 35, 0.06);
	--color-calendar-graph-day-L4-border: rgba(27, 31, 35, 0.06);
	--color-user-mention-fg: var(--color-fg-default);
	--color-user-mention-bg: var(--color-attention-subtle);
	--color-text-white: var(--color-scale-white);
}
:root {
	--Layout-pane-width: 220px;
	--Layout-content-width: 100%;
	--Layout-template-columns: 1fr var(--Layout-pane-width);
	--Layout-template-areas: "content pane";
	--Layout-column-gap: 16px;
	--Layout-row-gap: 16px;
	--Layout-outer-spacing-x: 0px;
	--Layout-outer-spacing-y: 0px;
	--Layout-inner-spacing-min: 0px;
	--Layout-inner-spacing-max: 0px;
}
'''
def swap_word_mask(radio_option):
    if(radio_option == "draw a mask above"):
        return gr.update(interactive=False, placeholder="Disabled")
    else:
        return gr.update(interactive=True, placeholder="A cat")

image_blocks = gr.Blocks(css=css)
with image_blocks as demo:
    gr.HTML(
        """
            <div style="text-align: center; max-width: 650px; margin: 0 auto;">
              <div
                style="
                  display: inline-flex;
                  align-items: center;
                  gap: 0.8rem;
                  font-size: 1.75rem;
                "
              >
                <svg
                  width="0.65em"
                  height="0.65em"
                  viewBox="0 0 115 115"
                  fill="none"
                  xmlns="http://www.w3.org/2000/svg"
                >
                  <rect width="23" height="23" fill="#AEAEAE"></rect>
                  <rect y="69" width="23" height="23" fill="black"></rect>
                  <rect x="23" width="23" height="23" fill="#AEAEAE"></rect>
                  <rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect>
                  <rect x="46" width="23" height="23" fill="#D9D9D9"></rect>
                  <rect x="46" y="69" width="23" height="23" fill="white"></rect>
                  <rect x="69" width="23" height="23" fill="black"></rect>
                  <rect x="69" y="69" width="23" height="23" fill="black"></rect>
                  <rect x="92" width="23" height="23" fill="#D9D9D9"></rect>
                  <rect x="92" y="69" width="23" height="23" fill="#AEAEAE"></rect>
                  <rect x="115" y="46" width="23" height="23" fill="white"></rect>
                  <rect x="115" y="115" width="23" height="23" fill="white"></rect>
                  <rect x="115" y="69" width="23" height="23" fill="#D9D9D9"></rect>
                  <rect x="92" y="46" width="23" height="23" fill="#AEAEAE"></rect>
                  <rect x="92" y="115" width="23" height="23" fill="#AEAEAE"></rect>
                  <rect x="92" y="69" width="23" height="23" fill="white"></rect>
                  <rect x="69" y="46" width="23" height="23" fill="white"></rect>
                  <rect x="69" y="115" width="23" height="23" fill="white"></rect>
                  <rect x="69" y="69" width="23" height="23" fill="#D9D9D9"></rect>
                  <rect x="46" y="46" width="23" height="23" fill="black"></rect>
                  <rect x="46" y="115" width="23" height="23" fill="black"></rect>
                  <rect x="46" y="69" width="23" height="23" fill="black"></rect>
                  <rect x="23" y="46" width="23" height="23" fill="#D9D9D9"></rect>
                  <rect x="23" y="115" width="23" height="23" fill="#AEAEAE"></rect>
                  <rect x="23" y="69" width="23" height="23" fill="black"></rect>
                </svg>
                <h1 style="font-weight: 900; margin-bottom: 7px;">
                  Stable Diffusion Multi Inpainting
                </h1>
              </div>
              <p style="margin-bottom: 10px; font-size: 94%">
                Inpaint Stable Diffusion by either drawing a mask or typing what to replace & what to keep !!!
              </p>
            </div>
        """
    )
    with gr.Row():
        with gr.Column():
            image = gr.Image(source='upload', tool='sketch', elem_id="image_upload", type="pil", label="Upload").style(height=400)
            with gr.Box(elem_id="mask_radio").style(border=False):
                radio = gr.Radio(["draw a mask above", "type what to mask below", "type what to keep"], value="draw a mask above", show_label=False, interactive=True).style(container=False)
                word_mask = gr.Textbox(label = "What to find in your image", interactive=False, elem_id="word_mask", placeholder="Disabled").style(container=False)
            prompt = gr.Textbox(label = 'Your prompt (what you want to add in place of what you are removing)')
            radio.change(fn=swap_word_mask, inputs=radio, outputs=word_mask,show_progress=False)
            radio.change(None, inputs=[], outputs=image_blocks, _js = """
            () => {
                css_style = document.styleSheets[document.styleSheets.length - 1]
                last_item = css_style.cssRules[css_style.cssRules.length - 1]
                last_item.style.display = ["flex", ""].includes(last_item.style.display) ? "none" : "flex";
            }""")
            btn = gr.Button("Run")
        with gr.Column():
            result = gr.Image(label="Result")
        btn.click(fn=predict, inputs=[radio, image, word_mask, prompt], outputs=result)
    gr.HTML(
            """
            <div class="footer">
                    <p>Model by <a href="https://huggingface.co/CompVis" style="text-decoration: underline;" target="_blank">CompVis</a> and <a href="https://huggingface.co/stabilityai" style="text-decoration: underline;" target="_blank">Stability AI</a> - Inpainting by <a href="https://github.com/" style="text-decoration: underline;" target="_blank">NightFury</a> using clipseg[model] with bit modification - Gradio Demo on 🤗 Hugging Face
                    </p>
                </div>
                
                
            <div id="readme" class="Box-body readme blob js-code-block-container p-5 p-xl-6 gist-border-0">
    <article class="markdown-body entry-content container-lg" itemprop="text"><h1 dir="auto"><a id="user-content-image-segmentation-using-text-and-image-prompts" class="anchor" aria-hidden="true" href="#image-segmentation-using-text-and-image-prompts"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Image Segmentation Using Text and Image Prompts</h1>
<p dir="auto">This repository contains the code used in the paper <a href="https://arxiv.org/abs/2112.10003" rel="nofollow">"Image Segmentation Using Text and Image Prompts"</a>.</p>
<p dir="auto"><strong>The Paper has been accepted to CVPR 2022!</strong></p>
<p dir="auto"><a target="_blank" rel="noopener noreferrer" href="/ThereforeGames/txt2mask/blob/main/repositories/clipseg/overview.png"><img src="/ThereforeGames/txt2mask/raw/main/repositories/clipseg/overview.png" alt="drawing" style="max-width: 100%;" height="200em"></a></p>
<p dir="auto">The systems allows to create segmentation models without training based on:</p>
<ul dir="auto">
<li>An arbitrary text query</li>
<li>Or an image with a mask highlighting stuff or an object.</li>
</ul>
<h3 dir="auto"><a id="user-content-quick-start" class="anchor" aria-hidden="true" href="#quick-start"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Quick Start</h3>
<p dir="auto">In the <code>Quickstart.ipynb</code> notebook we provide the code for using a pre-trained CLIPSeg model. If you run the notebook locally, make sure you downloaded the <code>rd64-uni.pth</code> weights, either manually or via git lfs extension.
It can also be used interactively using <a href="https://mybinder.org/v2/gh/timojl/clipseg/HEAD?labpath=Quickstart.ipynb" rel="nofollow">MyBinder</a>
(please note that the VM does not use a GPU, thus inference takes a few seconds).</p>
<h3 dir="auto"><a id="user-content-dependencies" class="anchor" aria-hidden="true" href="#dependencies"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Dependencies</h3>
<p dir="auto">This code base depends on pytorch, torchvision and clip (<code>pip install git+https://github.com/openai/CLIP.git</code>).
Additional dependencies are hidden for double blind review.</p>
<h3 dir="auto"><a id="user-content-datasets" class="anchor" aria-hidden="true" href="#datasets"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Datasets</h3>
<ul dir="auto">
<li><code>PhraseCut</code> and <code>PhraseCutPlus</code>: Referring expression dataset</li>
<li><code>PFEPascalWrapper</code>: Wrapper class for PFENet's Pascal-5i implementation</li>
<li><code>PascalZeroShot</code>: Wrapper class for PascalZeroShot</li>
<li><code>COCOWrapper</code>: Wrapper class for COCO.</li>
</ul>
<h3 dir="auto"><a id="user-content-models" class="anchor" aria-hidden="true" href="#models"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Models</h3>
<ul dir="auto">
<li><code>CLIPDensePredT</code>: CLIPSeg model with transformer-based decoder.</li>
<li><code>ViTDensePredT</code>: CLIPSeg model with transformer-based decoder.</li>
</ul>
<h3 dir="auto"><a id="user-content-third-party-dependencies" class="anchor" aria-hidden="true" href="#third-party-dependencies"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Third Party Dependencies</h3>
<p dir="auto">For some of the datasets third party dependencies are required. Run the following commands in the <code>third_party</code> folder.</p>
<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto"><pre>git clone https://github.com/cvlab-yonsei/JoEm
git clone https://github.com/Jia-Research-Lab/PFENet.git
git clone https://github.com/ChenyunWu/PhraseCutDataset.git
git clone https://github.com/juhongm999/hsnet.git</pre><div class="zeroclipboard-container position-absolute right-0 top-0">
    <clipboard-copy aria-label="Copy" class="ClipboardButton btn js-clipboard-copy m-2 p-0 tooltipped-no-delay" data-copy-feedback="Copied!" data-tooltip-direction="w" value="git clone https://github.com/cvlab-yonsei/JoEm
git clone https://github.com/Jia-Research-Lab/PFENet.git
git clone https://github.com/ChenyunWu/PhraseCutDataset.git
git clone https://github.com/juhongm999/hsnet.git" tabindex="0" role="button">
      <svg aria-hidden="true" height="16" viewBox="0 0 16 16" version="1.1" width="16" data-view-component="true" class="octicon octicon-copy js-clipboard-copy-icon m-2">
    <path fill-rule="evenodd" d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 010 1.5h-1.5a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-1.5a.75.75 0 011.5 0v1.5A1.75 1.75 0 019.25 16h-7.5A1.75 1.75 0 010 14.25v-7.5z"></path><path fill-rule="evenodd" d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0114.25 11h-7.5A1.75 1.75 0 015 9.25v-7.5zm1.75-.25a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-7.5a.25.25 0 00-.25-.25h-7.5z"></path>
</svg>
      <svg aria-hidden="true" height="16" viewBox="0 0 16 16" version="1.1" width="16" data-view-component="true" class="octicon octicon-check js-clipboard-check-icon color-fg-success d-none m-2">
    <path fill-rule="evenodd" d="M13.78 4.22a.75.75 0 010 1.06l-7.25 7.25a.75.75 0 01-1.06 0L2.22 9.28a.75.75 0 011.06-1.06L6 10.94l6.72-6.72a.75.75 0 011.06 0z"></path>
</svg>
    </clipboard-copy>
  </div></div>
<h3 dir="auto"><a id="user-content-weights" class="anchor" aria-hidden="true" href="#weights"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Weights</h3>
<p dir="auto">The MIT license does not apply to these weights.</p>
<ul dir="auto">
<li><a href="https://github.com/timojl/clipseg/raw/master/weights/rd64-uni.pth">CLIPSeg-D64</a> (4.1MB, without CLIP weights)</li>
<li><a href="https://github.com/timojl/clipseg/raw/master/weights/rd16-uni.pth">CLIPSeg-D16</a> (1.1MB, without CLIP weights)</li>
</ul>
<h3 dir="auto"><a id="user-content-training-and-evaluation" class="anchor" aria-hidden="true" href="#training-and-evaluation"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Training and Evaluation</h3>
<p dir="auto">To train use the <code>training.py</code> script with experiment file and experiment id parameters. E.g. <code>python training.py phrasecut.yaml 0</code> will train the first phrasecut experiment which is defined by the <code>configuration</code> and first <code>individual_configurations</code> parameters. Model weights will be written in <code>logs/</code>.</p>
<p dir="auto">For evaluation use <code>score.py</code>. E.g. <code>python score.py phrasecut.yaml 0 0</code> will train the first phrasecut experiment of <code>test_configuration</code> and the first configuration in <code>individual_configurations</code>.</p>
<h3 dir="auto"><a id="user-content-usage-of-pfenet-wrappers" class="anchor" aria-hidden="true" href="#usage-of-pfenet-wrappers"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>Usage of PFENet Wrappers</h3>
<p dir="auto">In order to use the dataset and model wrappers for PFENet, the PFENet repository needs to be cloned to the root folder.
<code>git clone https://github.com/Jia-Research-Lab/PFENet.git </code></p>
<h3 dir="auto"><a id="user-content-license" class="anchor" aria-hidden="true" href="#license"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path fill-rule="evenodd" d="M7.775 3.275a.75.75 0 001.06 1.06l1.25-1.25a2 2 0 112.83 2.83l-2.5 2.5a2 2 0 01-2.83 0 .75.75 0 00-1.06 1.06 3.5 3.5 0 004.95 0l2.5-2.5a3.5 3.5 0 00-4.95-4.95l-1.25 1.25zm-4.69 9.64a2 2 0 010-2.83l2.5-2.5a2 2 0 012.83 0 .75.75 0 001.06-1.06 3.5 3.5 0 00-4.95 0l-2.5 2.5a3.5 3.5 0 004.95 4.95l1.25-1.25a.75.75 0 00-1.06-1.06l-1.25 1.25a2 2 0 01-2.83 0z"></path></svg></a>License</h3>
<p dir="auto">The source code files in this repository (excluding model weights) are released under MIT license.</p>


</article>
  </div>
                <div class="acknowledgments">
                    <p><h4>LICENSE</h4>
The model is licensed with a <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" style="text-decoration: underline;" target="_blank">CreativeML Open RAIL-M</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
                    <p><h4>Biases and content acknowledgment</h4>
Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">model card</a></p>
               </div>
           """
        )
demo.launch()