ArcaneSVK2 / app.py
Podtekatel's picture
Update app.py
20428be
raw
history blame
2.45 kB
import logging
import os
import gradio as gr
import numpy as np
from PIL import Image
from huggingface_hub import hf_hub_url, hf_hub_download
from inference.face_detector import StatRetinaFaceDetector
from inference.model_pipeline import VSNetModelPipeline
from inference.onnx_model import ONNXModel
logging.basicConfig(
format='%(asctime)s %(levelname)-8s %(message)s',
level=logging.INFO,
datefmt='%Y-%m-%d %H:%M:%S')
MODEL_IMG_SIZE = 512
usage_count = 82 # Based on hugging face logs
def load_model():
REPO_ID = "Podtekatel/ArcaneVSK2"
FILENAME_OLD = "arcane_exp_230_ep_136_512_res_V2_lighter.onnx"
global model_old
global pipeline_old
# Old model
model_path = hf_hub_download(REPO_ID, FILENAME_OLD), use_auth_token=os.getenv('HF_TOKEN')
model_old = ONNXModel(model_path)
pipeline_old = VSNetModelPipeline(model_old, StatRetinaFaceDetector(MODEL_IMG_SIZE), background_resize=1024, no_detected_resize=1024)
return model_old
load_model()
def inference(img):
img = np.array(img)
out_img = pipeline_old(img)
out_img = Image.fromarray(out_img)
global usage_count
usage_count += 1
logging.info(f'Usage count is {usage_count}')
return out_img
title = "ARCNStyleTransferV2"
description = "Gradio Demo for Arcane Season 1 style transfer. To use it, simply upload your image, or click one of the examples to load them. Press ❤️ if you like this space!"
article = "This is one of my successful experiments on style transfer. I've built my own pipeline, generator model and private dataset to train this model<br>" \
"" \
"" \
"" \
"Model pipeline which used in project is improved CartoonGAN.<br>" \
"This model was trained on RTX 2080 Ti 3 days with batch size 7.<br>" \
"Model weights 80 MB in ONNX fp32 format, infers 100 ms on GPU and 600 ms on CPU at 512x512 resolution.<br>" \
"If you want to use this app or integrate this model into yours, please contact me at email '[email protected]'."
imgs_folder = 'demo'
examples = [[os.path.join(imgs_folder, img_filename)] for img_filename in sorted(os.listdir(imgs_folder))]
demo = gr.Interface(
fn=inference,
inputs=[gr.inputs.Image(type="pil")],
outputs=gr.outputs.Image(type="pil"),
title=title,
description=description,
article=article,
examples=examples)
demo.queue(concurrency_count=1)
demo.launch()