| 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 = ["tatoo.jpg","tattoo2.jpg"] | |
| 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('Predict') | |
| 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('Predict') | |
| if pressed: | |
| st.empty() | |
| st.sidebar.write('Please wait for the magic to happen! This may take up to a minute.') | |
| predict(uploaded_file) |