CatDogs / app.py
Kseniiashk's picture
Upload app.py with huggingface_hub
bffe51c verified
Raw History Blame Contribute Delete
3.82 kB
import streamlit as st
import torch
import torch.nn as nn
from torchvision import transforms
from PIL import Image
import numpy as np
class ResidualBlock(nn.Module):
def __init__(self, channels):
super().__init__()
self.block = nn.Sequential(
nn.ReflectionPad2d(1),
nn.Conv2d(channels, channels, 3),
nn.InstanceNorm2d(channels),
nn.ReLU(inplace=True),
nn.ReflectionPad2d(1),
nn.Conv2d(channels, channels, 3),
nn.InstanceNorm2d(channels),
)
def forward(self, x):
return x + self.block(x)
class ResNetGenerator(nn.Module):
def __init__(self, in_ch=3, out_ch=3, ngf=32, n_blocks=6):
super().__init__()
layers = [
nn.ReflectionPad2d(3),
nn.Conv2d(in_ch, ngf, 7),
nn.InstanceNorm2d(ngf),
nn.ReLU(inplace=True),
]
mult = 1
for i in range(2):
layers += [
nn.Conv2d(ngf * mult, ngf * mult * 2, 3, stride=2, padding=1),
nn.InstanceNorm2d(ngf * mult * 2),
nn.ReLU(inplace=True),
]
mult *= 2
for _ in range(n_blocks):
layers.append(ResidualBlock(ngf * mult))
for i in range(2):
layers += [
nn.ConvTranspose2d(ngf * mult, ngf * mult // 2, 3, stride=2, padding=1, output_padding=1),
nn.InstanceNorm2d(ngf * mult // 2),
nn.ReLU(inplace=True),
]
mult //= 2
layers += [nn.ReflectionPad2d(3), nn.Conv2d(ngf, out_ch, 7), nn.Tanh()]
self.model = nn.Sequential(*layers)
def forward(self, x):
return self.model(x)
@st.cache_resource
def load_models():
device = torch.device("cpu")
checkpoint = torch.load("cyclegan_dogs2cats_final.pt", map_location=device)
prefix_ab = "generators.a_to_b."
prefix_ba = "generators.b_to_a."
state_ab = {k[len(prefix_ab):]: v for k, v in checkpoint.items() if k.startswith(prefix_ab)}
state_ba = {k[len(prefix_ba):]: v for k, v in checkpoint.items() if k.startswith(prefix_ba)}
gen_ab = ResNetGenerator(ngf=32, n_blocks=6)
gen_ba = ResNetGenerator(ngf=32, n_blocks=6)
gen_ab.load_state_dict(state_ab)
gen_ba.load_state_dict(state_ba)
gen_ab.eval()
gen_ba.eval()
return gen_ab, gen_ba
def preprocess(image):
transform = transforms.Compose([
transforms.Resize((128, 128)),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
])
return transform(image).unsqueeze(0)
def postprocess(tensor):
img = tensor.squeeze(0).detach().cpu().numpy()
img = (img * 0.5 + 0.5).clip(0, 1)
img = (img.transpose(1, 2, 0) * 255).astype(np.uint8)
return Image.fromarray(img)
def main():
st.set_page_config(page_title="CycleGAN: Dogs & Cats", layout="centered")
st.title("CycleGAN: Dogs ↔ Cats")
gen_ab, gen_ba = load_models()
direction = st.radio("Направление трансформации", ["Dog → Cat", "Cat → Dog"])
uploaded = st.file_uploader("Загрузите изображение", type=["jpg", "jpeg", "png", "webp", "bmp"])
if uploaded is not None:
image = Image.open(uploaded).convert("RGB")
col1, col2 = st.columns(2)
col1.subheader("Оригинал")
col1.image(image, use_container_width=True)
inp = preprocess(image)
with torch.no_grad():
if direction == "Dog → Cat":
out = gen_ab(inp)
else:
out = gen_ba(inp)
result = postprocess(out)
col2.subheader("Результат")
col2.image(result, use_container_width=True)
if __name__ == "__main__":
main()