Spaces:
Runtime error
Runtime error
File size: 23,369 Bytes
cbba703 374a0d6 cbba703 ae3aed8 f00ee3e ec1e968 374a0d6 4cd058c 374a0d6 c305a03 6faef3f ec1e968 4cd058c cb97d35 f00ee3e a3f2113 f00ee3e 199d28b cbba703 14f47c2 6770691 cbba703 6770691 cbba703 c84b0ab 6770691 c84b0ab 6770691 cbba703 c84b0ab cbba703 31f6f75 cbba703 31f6f75 cbba703 b61fad9 31f6f75 f949a41 b61fad9 31f6f75 b61fad9 cbba703 31f6f75 cbba703 b61fad9 cbba703 e9d5a30 cbba703 d4a60e3 cbba703 d4a60e3 cbba703 a3f2113 cbba703 a3f2113 cbba703 31f6f75 cbba703 31f6f75 cbba703 31f6f75 cbba703 31f6f75 cbba703 a3f2113 cbba703 b61fad9 cbba703 34abcdd cbba703 3ad2222 b61fad9 cbba703 3ad2222 378dc00 fa1fa15 3ad2222 14f47c2 3ad2222 34abcdd 3ad2222 34abcdd 3ad2222 34abcdd 3ad2222 34abcdd 3ad2222 34abcdd 3ad2222 34abcdd 3ad2222 34abcdd 3ad2222 0cfe17d 34abcdd 3ad2222 0cfe17d 34abcdd 3ad2222 0cfe17d 34abcdd 3ad2222 0cfe17d 34abcdd cbba703 0cfe17d fa1fa15 0cfe17d cbba703 374a0d6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 |
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 = "cpu" #"cuda" if torch.cuda.is_available() else "cpu"
model_id_or_path = "CompVis/stable-diffusion-v1-4"
pipe = StableDiffusionInpaintingPipeline.from_pretrained(
model_id_or_path,
revision="fp16",
torch_dtype=torch.long, #float16
use_auth_token=auth_token
)
#self.register_buffer('n_', ...)
print ("torch.backends.mps.is_available: ", torch.backends.mps.is_available())
pipe = pipe.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=True) #False
imgRes = 256
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
transforms.Resize((imgRes, imgRes)),
])
def predict(radio, dict, word_mask, prompt=""):
if(radio == "draw a mask above"):
with autocast(device): #"cuda"
init_image = dict["image"].convert("RGB").resize((imgRes, imgRes))
mask = dict["mask"].convert("RGB").resize((imgRes, imgRes))
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((imgRes, imgRes))
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((imgRes, imgRes))
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}
'''
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="black"></rect>
<rect x="115" y="115" width="23" height="23" fill="black"></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="black"></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="white"></rect>
<rect x="46" y="115" width="23" height="23" fill="black"></rect>
<rect x="46" y="69" width="23" height="23" fill="white"></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)
img_res = gr.Dropdown(['512*512', '256*256'], label="Image Resolution")
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 class="acknowledgments" >
<h1 dir="auto"><a id="user-content-image-segmentation-using-text-and-image-prompts" 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"><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" 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" 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" 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" 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" 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 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 >
<clipboard-copy aria-label="Copy" 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" 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" 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" 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>
<h4 dir="auto"><a id="user-content-license" 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</h4>
<p dir="auto">The source code files in this repository (excluding model weights) are released under MIT license.</p>
<p>
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()
|