|
import streamlit as st |
|
import urllib.request |
|
import PIL.Image |
|
from PIL import Image |
|
import requests |
|
import fastai |
|
from fastai.vision import * |
|
from fastai.utils.mem import * |
|
from fastai.vision import open_image, load_learner, image, torch |
|
import numpy as np |
|
from urllib.request import urlretrieve |
|
from io import BytesIO |
|
import numpy as np |
|
import torchvision.transforms as T |
|
from PIL import Image,ImageOps,ImageFilter |
|
from io import BytesIO |
|
import os |
|
|
|
|
|
|
|
class FeatureLoss(nn.Module): |
|
def __init__(self, m_feat, layer_ids, layer_wgts): |
|
super().__init__() |
|
self.m_feat = m_feat |
|
self.loss_features = [self.m_feat[i] for i in layer_ids] |
|
self.hooks = hook_outputs(self.loss_features, detach=False) |
|
self.wgts = layer_wgts |
|
self.metric_names = ['pixel',] + [f'feat_{i}' for i in range(len(layer_ids)) |
|
] + [f'gram_{i}' for i in range(len(layer_ids))] |
|
|
|
def make_features(self, x, clone=False): |
|
self.m_feat(x) |
|
return [(o.clone() if clone else o) for o in self.hooks.stored] |
|
|
|
def forward(self, input, target): |
|
out_feat = self.make_features(target, clone=True) |
|
in_feat = self.make_features(input) |
|
self.feat_losses = [base_loss(input,target)] |
|
self.feat_losses += [base_loss(f_in, f_out)*w |
|
for f_in, f_out, w in zip(in_feat, out_feat, self.wgts)] |
|
self.feat_losses += [base_loss(gram_matrix(f_in), gram_matrix(f_out))*w**2 * 5e3 |
|
for f_in, f_out, w in zip(in_feat, out_feat, self.wgts)] |
|
self.metrics = dict(zip(self.metric_names, self.feat_losses)) |
|
return sum(self.feat_losses) |
|
|
|
def __del__(self): self.hooks.remove() |
|
|
|
|
|
MODEL_URL = "https://www.dropbox.com/s/vxgw0s7ktpla4dk/SkinDeep2.pkl?dl=1" |
|
urlretrieve(MODEL_URL, "SkinDeep2.pkl") |
|
path = Path(".") |
|
learn = load_learner(path, 'SkinDeep2.pkl') |
|
|
|
|
|
def predict(image): |
|
img_fast = open_image(image) |
|
a = PIL.Image.open(image).convert('RGB') |
|
st.image(a, caption='Input') |
|
p,img_hr,b = learn.predict(img_fast) |
|
x = np.minimum(np.maximum(image2np(img_hr.data*255), 0), 255).astype(np.uint8) |
|
img = PIL.Image.fromarray(x).convert('RGB') |
|
return st.image(img, caption='Tattoo') |
|
|
|
|
|
SIDEBAR_OPTION_DEMO_IMAGE = "Select a Demo Image" |
|
SIDEBAR_OPTION_UPLOAD_IMAGE = "Upload an Image" |
|
|
|
SIDEBAR_OPTIONS = [SIDEBAR_OPTION_DEMO_IMAGE, SIDEBAR_OPTION_UPLOAD_IMAGE] |
|
|
|
app_mode = st.sidebar.selectbox("Please select from the following", SIDEBAR_OPTIONS) |
|
photos = ["fight.jpg","shaolin-kung-fu.jpg","unnamed.jpg","michael-jackson.png"] |
|
|
|
if app_mode == SIDEBAR_OPTION_DEMO_IMAGE: |
|
st.sidebar.write(" ------ ") |
|
option = st.sidebar.selectbox('Please select a sample image and then click PoP button', photos) |
|
pressed = st.sidebar.button('PoP') |
|
if pressed: |
|
st.empty() |
|
st.sidebar.write('Please wait for the magic to happen! This may take up to a minute.') |
|
predict(option) |
|
|
|
|
|
elif app_mode == SIDEBAR_OPTION_UPLOAD_IMAGE: |
|
uploaded_file = st.file_uploader("Choose an image...") |
|
if uploaded_file is not None: |
|
pressed = st.sidebar.button('PoP') |
|
if pressed: |
|
st.empty() |
|
st.sidebar.write('Please wait for the magic to happen! This may take up to a minute.') |
|
predict(uploaded_file) |