File size: 7,201 Bytes
44425c0 |
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 |
import json
import gradio as gr
from PIL import Image
import safetensors.torch
import timm
from timm.models import VisionTransformer
import torch
from torchvision.transforms import transforms
from torchvision.transforms import InterpolationMode
import torchvision.transforms.functional as TF
torch.set_grad_enabled(False)
class Fit(torch.nn.Module):
def __init__(
self,
bounds: tuple[int, int] | int,
interpolation = InterpolationMode.LANCZOS,
grow: bool = True,
pad: float | None = None
):
super().__init__()
self.bounds = (bounds, bounds) if isinstance(bounds, int) else bounds
self.interpolation = interpolation
self.grow = grow
self.pad = pad
def forward(self, img: Image) -> Image:
wimg, himg = img.size
hbound, wbound = self.bounds
hscale = hbound / himg
wscale = wbound / wimg
if not self.grow:
hscale = min(hscale, 1.0)
wscale = min(wscale, 1.0)
scale = min(hscale, wscale)
if scale == 1.0:
return img
hnew = min(round(himg * scale), hbound)
wnew = min(round(wimg * scale), wbound)
img = TF.resize(img, (hnew, wnew), self.interpolation)
if self.pad is None:
return img
hpad = hbound - hnew
wpad = wbound - wnew
tpad = hpad // 2
bpad = hpad - tpad
lpad = wpad // 2
rpad = wpad - lpad
return TF.pad(img, (lpad, tpad, rpad, bpad), self.pad)
def __repr__(self) -> str:
return (
f"{self.__class__.__name__}(" +
f"bounds={self.bounds}, " +
f"interpolation={self.interpolation.value}, " +
f"grow={self.grow}, " +
f"pad={self.pad})"
)
class CompositeAlpha(torch.nn.Module):
def __init__(
self,
background: tuple[float, float, float] | float,
):
super().__init__()
self.background = (background, background, background) if isinstance(background, float) else background
self.background = torch.tensor(self.background).unsqueeze(1).unsqueeze(2)
def forward(self, img: torch.Tensor) -> torch.Tensor:
if img.shape[-3] == 3:
return img
alpha = img[..., 3, None, :, :]
img[..., :3, :, :] *= alpha
background = self.background.expand(-1, img.shape[-2], img.shape[-1])
if background.ndim == 1:
background = background[:, None, None]
elif background.ndim == 2:
background = background[None, :, :]
img[..., :3, :, :] += (1.0 - alpha) * background
return img[..., :3, :, :]
def __repr__(self) -> str:
return (
f"{self.__class__.__name__}(" +
f"background={self.background})"
)
transform = transforms.Compose([
Fit((384, 384)),
transforms.ToTensor(),
CompositeAlpha(0.5),
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5], inplace=True),
transforms.CenterCrop((384, 384)),
])
model = timm.create_model(
"vit_so400m_patch14_siglip_384.webli",
pretrained=False,
num_classes=9083,
) # type: VisionTransformer
class GatedHead(torch.nn.Module):
def __init__(self,
num_features: int,
num_classes: int
):
super().__init__()
self.num_classes = num_classes
self.linear = torch.nn.Linear(num_features, num_classes * 2)
self.act = torch.nn.Sigmoid()
self.gate = torch.nn.Sigmoid()
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = self.linear(x)
x = self.act(x[:, :self.num_classes]) * self.gate(x[:, self.num_classes:])
return x
model.head = GatedHead(min(model.head.weight.shape), 9083)
safetensors.torch.load_model(model, "JTP_PILOT2-2-e3-vit_so400m_patch14_siglip_384.safetensors")
if torch.cuda.is_available():
model.cuda()
if torch.cuda.get_device_capability()[0] >= 7: # tensor cores
model.to(dtype=torch.float16, memory_format=torch.channels_last)
model.eval()
with open("tagger_tags.json", "r") as file:
tags = json.load(file) # type: dict
allowed_tags = list(tags.keys())
for idx, tag in enumerate(allowed_tags):
allowed_tags[idx] = tag.replace("_", " ")
sorted_tag_score = {}
def run_classifier(image, threshold):
global sorted_tag_score
img = image.convert('RGB')
tensor = transform(img).unsqueeze(0)
if torch.cuda.is_available():
tensor = tensor.cuda()
if torch.cuda.get_device_capability()[0] >= 7: # tensor cores
tensor = tensor.to(dtype=torch.float16, memory_format=torch.channels_last)
with torch.no_grad():
probits = model(tensor)[0].cpu()
values, indices = probits.topk(250)
tag_score = dict()
for i in range(indices.size(0)):
tag_score[allowed_tags[indices[i]]] = values[i].item()
sorted_tag_score = dict(sorted(tag_score.items(), key=lambda item: item[1], reverse=True))
return create_tags(threshold)
def create_tags(threshold):
global sorted_tag_score
filtered_tag_score = {key: value for key, value in sorted_tag_score.items() if value > threshold}
text_no_impl = ", ".join(filtered_tag_score.keys())
return text_no_impl, filtered_tag_score
def clear_image():
global sorted_tag_score
sorted_tag_score = {}
return "", {}
with gr.Blocks(css=".output-class { display: none; }") as demo:
gr.Markdown("""
## Joint Tagger Project: JTP-PILOT² Demo **BETA**
This tagger is designed for use on furry images (though may very well work on out-of-distribution images, potentially with funny results). A threshold of 0.2 is recommended. Lower thresholds often turn up more valid tags, but can also result in some amount of hallucinated tags.
This tagger is the result of joint efforts between members of the RedRocket team, with distinctions given to Thessalo for creating the foundation for this project with his efforts, RedHotTensors for redesigning the process into a second-order method that models information expectation, and drhead for dataset prep, creation of training code and supervision of training runs.
Special thanks to Minotoro at frosting.ai for providing the compute power for this project.
""")
with gr.Row():
with gr.Column():
image_input = gr.Image(label="Source", sources=['upload'], type='pil', height=512, show_label=False)
threshold_slider = gr.Slider(minimum=0.00, maximum=1.00, step=0.01, value=0.20, label="Threshold")
with gr.Column():
tag_string = gr.Textbox(label="Tag String")
label_box = gr.Label(label="Tag Predictions", num_top_classes=250, show_label=False)
image_input.upload(
fn=run_classifier,
inputs=[image_input, threshold_slider],
outputs=[tag_string, label_box]
)
image_input.clear(
fn=clear_image,
inputs=[],
outputs=[tag_string, label_box]
)
threshold_slider.input(
fn=create_tags,
inputs=[threshold_slider],
outputs=[tag_string, label_box]
)
if __name__ == "__main__":
demo.launch() |