|
|
|
|
|
from __future__ import annotations |
|
|
|
import functools |
|
import os |
|
import pathlib |
|
import sys |
|
import tarfile |
|
|
|
import gradio as gr |
|
import huggingface_hub |
|
import PIL.Image |
|
import torch |
|
import torchvision |
|
|
|
sys.path.insert(0, "bizarre-pose-estimator") |
|
|
|
from _util.twodee_v0 import I as ImageWrapper |
|
|
|
DESCRIPTION = "# [ShuhongChen/bizarre-pose-estimator (tagger)](https://github.com/ShuhongChen/bizarre-pose-estimator)" |
|
|
|
MODEL_REPO = "public-data/bizarre-pose-estimator-models" |
|
|
|
|
|
def load_sample_image_paths() -> list[pathlib.Path]: |
|
image_dir = pathlib.Path("images") |
|
if not image_dir.exists(): |
|
dataset_repo = "hysts/sample-images-TADNE" |
|
path = huggingface_hub.hf_hub_download(dataset_repo, "images.tar.gz", repo_type="dataset") |
|
with tarfile.open(path) as f: |
|
f.extractall() |
|
return sorted(image_dir.glob("*")) |
|
|
|
|
|
def load_model(device: torch.device) -> torch.nn.Module: |
|
path = huggingface_hub.hf_hub_download(MODEL_REPO, "tagger.pth") |
|
state_dict = torch.load(path) |
|
model = torchvision.models.resnet50(num_classes=1062) |
|
model.load_state_dict(state_dict) |
|
model.to(device) |
|
model.eval() |
|
return model |
|
|
|
|
|
def load_labels() -> list[str]: |
|
label_path = huggingface_hub.hf_hub_download(MODEL_REPO, "tags.txt") |
|
with open(label_path) as f: |
|
labels = [line.strip() for line in f.readlines()] |
|
return labels |
|
|
|
|
|
@torch.inference_mode() |
|
def predict( |
|
image: PIL.Image.Image, score_threshold: float, device: torch.device, model: torch.nn.Module, labels: list[str] |
|
) -> dict[str, float]: |
|
data = ImageWrapper(image).resize_square(256).alpha_bg(c="w").convert("RGB").tensor() |
|
data = data.to(device).unsqueeze(0) |
|
|
|
preds = model(data)[0] |
|
preds = torch.sigmoid(preds) |
|
preds = preds.cpu().numpy().astype(float) |
|
|
|
res = dict() |
|
for prob, label in zip(preds.tolist(), labels): |
|
if prob < score_threshold: |
|
continue |
|
res[label] = prob |
|
return res |
|
|
|
|
|
image_paths = load_sample_image_paths() |
|
examples = [[path.as_posix(), 0.5] for path in image_paths] |
|
|
|
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") |
|
model = load_model(device) |
|
labels = load_labels() |
|
|
|
fn = functools.partial(predict, device=device, model=model, labels=labels) |
|
|
|
with gr.Blocks(css="style.css") as demo: |
|
gr.Markdown(DESCRIPTION) |
|
with gr.Row(): |
|
with gr.Column(): |
|
image = gr.Image(label="Input", type="pil") |
|
threshold = gr.Slider(label="Score Threshold", minimum=0, maximum=1, step=0.05, value=0.5) |
|
run_button = gr.Button("Run") |
|
with gr.Column(): |
|
result = gr.Label(label="Output") |
|
|
|
inputs = [image, threshold] |
|
gr.Examples( |
|
examples=examples, |
|
inputs=inputs, |
|
outputs=result, |
|
fn=fn, |
|
cache_examples=os.getenv("CACHE_EXAMPLES") == "1", |
|
) |
|
run_button.click( |
|
fn=fn, |
|
inputs=inputs, |
|
outputs=result, |
|
api_name="predict", |
|
) |
|
|
|
if __name__ == "__main__": |
|
demo.queue(max_size=15).launch() |
|
|
