update to latest version

.pre-commit-config.yaml

@@ -1,61 +1,46 @@
-exclude: ^patch
+exclude: ^(Text2Human|patch)
 repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
-    hooks:
-      - id: check-executables-have-shebangs
-      - id: check-json
-      - id: check-merge-conflict
-      - id: check-shebang-scripts-are-executable
-      - id: check-toml
-      - id: check-yaml
-      - id: end-of-file-fixer
-      - id: mixed-line-ending
-        args: ["--fix=lf"]
-      - id: requirements-txt-fixer
-      - id: trailing-whitespace
-  - repo: https://github.com/myint/docformatter
-    rev: v1.7.5
-    hooks:
-      - id: docformatter
-        args: ["--in-place"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
-    hooks:
-      - id: isort
-        args: ["--profile", "black"]
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.10.0
-    hooks:
-      - id: mypy
-        args: ["--ignore-missing-imports"]
-        additional_dependencies:
-          [
-            "types-python-slugify",
-            "types-requests",
-            "types-PyYAML",
-            "types-pytz",
-          ]
-  - repo: https://github.com/psf/black
-    rev: 24.4.2
-    hooks:
-      - id: black
-        language_version: python3.10
-        args: ["--line-length", "119"]
-  - repo: https://github.com/kynan/nbstripout
-    rev: 0.7.1
-    hooks:
-      - id: nbstripout
-        args:
-          [
-            "--extra-keys",
-            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
-          ]
-  - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.5
-    hooks:
-      - id: nbqa-black
-      - id: nbqa-pyupgrade
-        args: ["--py37-plus"]
-      - id: nbqa-isort
-        args: ["--float-to-top"]
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.2.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: double-quote-string-fixer
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ['--fix=lf']
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.4
+  hooks:
+  - id: docformatter
+    args: ['--in-place']
+- repo: https://github.com/pycqa/isort
+  rev: 5.10.1
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.812
+  hooks:
+    - id: mypy
+      args: ['--ignore-missing-imports']
+- repo: https://github.com/google/yapf
+  rev: v0.32.0
+  hooks:
+  - id: yapf
+    args: ['--parallel', '--in-place']
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.5.0
+  hooks:
+    - id: nbstripout
+      args: ['--extra-keys', 'metadata.interpreter metadata.kernelspec cell.metadata.pycharm']
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.3.1
+  hooks:
+    - id: nbqa-isort
+    - id: nbqa-yapf

.style.yapf

@@ -0,0 +1,5 @@
+[style]
+based_on_style = pep8
+blank_line_before_nested_class_or_def = false
+spaces_before_comment = 2
+split_before_logical_operator = true

README.md

@@ -4,10 +4,9 @@ emoji: 🏃
 colorFrom: purple
 colorTo: gray
 sdk: gradio
-sdk_version: 4.36.1
+sdk_version: 3.0.13
 app_file: app.py
 pinned: false
-suggested_hardware: t4-small
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -2,132 +2,152 @@
 
 from __future__ import annotations
 
+import argparse
 import os
 import pathlib
-import random
-import shlex
 import subprocess
 
-if os.getenv("SYSTEM") == "spaces":
-    subprocess.run(shlex.split("pip install click==7.1.2"))
-    subprocess.run(shlex.split("pip install typer==0.9.4"))
-
-    import mim
-
-    mim.uninstall("mmcv-full", confirm_yes=True)
-    mim.install("mmcv-full==1.5.2", is_yes=True)
-
-    with open("patch") as f:
-        subprocess.run(shlex.split("patch -p1"), cwd="Text2Human", stdin=f)
-
-
 import gradio as gr
-import numpy as np
+
+if os.getenv('SYSTEM') == 'spaces':
+    subprocess.call('pip uninstall -y mmcv-full'.split())
+    subprocess.call('pip install mmcv-full==1.5.2'.split())
+    subprocess.call('git apply ../patch'.split(), cwd='Text2Human')
 
 from model import Model
 
-DESCRIPTION = """# [Text2Human](https://github.com/yumingj/Text2Human)
+DESCRIPTION = '''# Text2Human
 
+This is an unofficial demo for <a href="https://github.com/yumingj/Text2Human">https://github.com/yumingj/Text2Human</a>.
 You can modify sample steps and seeds. By varying seeds, you can sample different human images under the same pose, shape description, and texture description. The larger the sample steps, the better quality of the generated images. (The default value of sample steps is 256 in the original repo.)
 
 Label image generation step can be skipped. However, in that case, the input label image must be 512x256 in size and must contain only the specified colors.
-"""
-
-MAX_SEED = np.iinfo(np.int32).max
-
-
-def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-    return seed
-
-
-model = Model()
-
-with gr.Blocks(css="style.css") as demo:
-    gr.Markdown(DESCRIPTION)
-
-    with gr.Row():
-        with gr.Column():
-            with gr.Row():
-                input_image = gr.Image(label="Input Pose Image", type="pil", elem_id="input-image")
-                pose_data = gr.State()
-            with gr.Row():
-                paths = sorted(pathlib.Path("pose_images").glob("*.png"))
-                gr.Examples(examples=[[path.as_posix()] for path in paths], inputs=input_image)
-
-            with gr.Row():
-                shape_text = gr.Textbox(
-                    label="Shape Description",
-                    placeholder="""<gender>, <sleeve length>, <length of lower clothing>, <outer clothing type>, <other accessories1>, ...
-Note: The outer clothing type and accessories can be omitted.""",
-                )
-            with gr.Row():
-                gr.Examples(
-                    examples=[["man, sleeveless T-shirt, long pants"], ["woman, short-sleeve T-shirt, short jeans"]],
-                    inputs=shape_text,
-                )
-            with gr.Row():
-                generate_label_button = gr.Button("Generate Label Image")
-
-        with gr.Column():
-            with gr.Row():
-                label_image = gr.Image(label="Label Image", type="numpy", format="png", elem_id="label-image")
-
-            with gr.Row():
-                texture_text = gr.Textbox(
-                    label="Texture Description",
-                    placeholder="""<upper clothing texture>, <lower clothing texture>, <outer clothing texture>
-Note: Currently, only 5 types of textures are supported, i.e., pure color, stripe/spline, plaid/lattice, floral, denim.""",
-                )
-            with gr.Row():
-                gr.Examples(
-                    examples=[
-                        ["pure color, denim"],
-                        ["floral, stripe"],
-                    ],
-                    inputs=texture_text,
-                )
-            with gr.Row():
-                sample_steps = gr.Slider(label="Sample Steps", minimum=10, maximum=300, step=1, value=256)
-            with gr.Row():
-                seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
-                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            with gr.Row():
-                generate_human_button = gr.Button("Generate Human")
-
-        with gr.Column():
-            with gr.Row():
-                result = gr.Image(label="Result")
-
-    input_image.change(
-        fn=model.process_pose_image,
-        inputs=input_image,
-        outputs=pose_data,
-    )
-    generate_label_button.click(
-        fn=model.generate_label_image,
-        inputs=[
-            pose_data,
-            shape_text,
-        ],
-        outputs=label_image,
-    )
-    generate_human_button.click(
-        fn=randomize_seed_fn,
-        inputs=[seed, randomize_seed],
-        outputs=seed,
-        queue=False,
-    ).then(
-        fn=model.generate_human,
-        inputs=[
-            label_image,
-            texture_text,
-            sample_steps,
-            seed,
-        ],
-        outputs=result,
+'''
+FOOTER = '<img id="visitor-badge" alt="visitor badge" src="https://visitor-badge.glitch.me/badge?page_id=hysts.text2human" />'
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--device', type=str, default='cpu')
+    parser.add_argument('--theme', type=str)
+    parser.add_argument('--share', action='store_true')
+    parser.add_argument('--port', type=int)
+    parser.add_argument('--disable-queue',
+                        dest='enable_queue',
+                        action='store_false')
+    return parser.parse_args()
+
+
+def set_example_image(example: list) -> dict:
+    return gr.Image.update(value=example[0])
+
+
+def set_example_text(example: list) -> dict:
+    return gr.Textbox.update(value=example[0])
+
+
+def main():
+    args = parse_args()
+    model = Model(args.device)
+
+    with gr.Blocks(theme=args.theme, css='style.css') as demo:
+        gr.Markdown(DESCRIPTION)
+
+        with gr.Row():
+            with gr.Column():
+                with gr.Row():
+                    input_image = gr.Image(label='Input Pose Image',
+                                           type='pil',
+                                           elem_id='input-image')
+                    pose_data = gr.Variable()
+                with gr.Row():
+                    paths = sorted(pathlib.Path('pose_images').glob('*.png'))
+                    example_images = gr.Dataset(components=[input_image],
+                                                samples=[[path.as_posix()]
+                                                         for path in paths])
+                with gr.Row():
+                    shape_text = gr.Textbox(
+                        label='Shape Description',
+                        placeholder=
+                        '''<gender>, <sleeve length>, <length of lower clothing>, <outer clothing type>, <other accessories1>, ...
+Note: The outer clothing type and accessories can be omitted.''')
+                with gr.Row():
+                    shape_example_texts = gr.Dataset(
+                        components=[shape_text],
+                        samples=[['man, sleeveless T-shirt, long pants'],
+                                 ['woman, short-sleeve T-shirt, short jeans']])
+                with gr.Row():
+                    generate_label_button = gr.Button('Generate Label Image')
+
+            with gr.Column():
+                with gr.Row():
+                    label_image = gr.Image(label='Label Image',
+                                           type='numpy',
+                                           elem_id='label-image')
+                with gr.Row():
+                    texture_text = gr.Textbox(
+                        label='Texture Description',
+                        placeholder=
+                        '''<upper clothing texture>, <lower clothing texture>, <outer clothing texture>
+Note: Currently, only 5 types of textures are supported, i.e., pure color, stripe/spline, plaid/lattice, floral, denim.'''
+                    )
+                with gr.Row():
+                    texture_example_texts = gr.Dataset(
+                        components=[texture_text],
+                        samples=[['pure color, denim'], ['floral, stripe']])
+                with gr.Row():
+                    sample_steps = gr.Slider(10,
+                                             300,
+                                             value=10,
+                                             step=10,
+                                             label='Sample Steps')
+                with gr.Row():
+                    seed = gr.Slider(0, 1000000, value=0, step=1, label='Seed')
+                with gr.Row():
+                    generate_human_button = gr.Button('Generate Human')
+
+            with gr.Column():
+                with gr.Row():
+                    result = gr.Image(label='Result',
+                                      type='numpy',
+                                      elem_id='result-image')
+
+        gr.Markdown(FOOTER)
+
+        input_image.change(fn=model.process_pose_image,
+                           inputs=input_image,
+                           outputs=pose_data)
+        generate_label_button.click(fn=model.generate_label_image,
+                                    inputs=[
+                                        pose_data,
+                                        shape_text,
+                                    ],
+                                    outputs=label_image)
+        generate_human_button.click(fn=model.generate_human,
+                                    inputs=[
+                                        label_image,
+                                        texture_text,
+                                        sample_steps,
+                                        seed,
+                                    ],
+                                    outputs=result)
+        example_images.click(fn=set_example_image,
+                             inputs=example_images,
+                             outputs=example_images.components)
+        shape_example_texts.click(fn=set_example_text,
+                                  inputs=shape_example_texts,
+                                  outputs=shape_example_texts.components)
+        texture_example_texts.click(fn=set_example_text,
+                                    inputs=texture_example_texts,
+                                    outputs=texture_example_texts.components)
+
+    demo.launch(
+        enable_queue=args.enable_queue,
+        server_port=args.port,
+        share=args.share,
+        debug=True,
     )
 
-if __name__ == "__main__":
-    demo.queue(max_size=10).launch()
+
+if __name__ == '__main__':
+    main()

model.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import logging
+import os
 import pathlib
 import sys
 import zipfile
@@ -9,13 +11,25 @@ import numpy as np
 import PIL.Image
 import torch
 
-sys.path.insert(0, "Text2Human")
+sys.path.insert(0, 'Text2Human')
 
 from models.sample_model import SampleFromPoseModel
-from utils.language_utils import generate_shape_attributes, generate_texture_attributes
+from utils.language_utils import (generate_shape_attributes,
+                                  generate_texture_attributes)
 from utils.options import dict_to_nonedict, parse
 from utils.util import set_random_seed
 
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.DEBUG)
+logger.propagate = False
+formatter = logging.Formatter(
+    '[%(asctime)s] %(name)s %(levelname)s: %(message)s',
+    datefmt='%Y-%m-%d %H:%M:%S')
+handler = logging.StreamHandler(stream=sys.stdout)
+handler.setLevel(logging.DEBUG)
+handler.setFormatter(formatter)
+logger.addHandler(handler)
+
 COLOR_LIST = [
     (0, 0, 0),
     (255, 250, 250),
@@ -45,44 +59,53 @@ COLOR_LIST = [
 
 
 class Model:
-    def __init__(self):
-        device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    def __init__(self, device: str):
         self.config = self._load_config()
-        self.config["device"] = device.type
+        self.config['device'] = device
         self._download_models()
         self.model = SampleFromPoseModel(self.config)
         self.model.batch_size = 1
 
     def _load_config(self) -> dict:
-        path = "Text2Human/configs/sample_from_pose.yml"
+        path = 'Text2Human/configs/sample_from_pose.yml'
         config = parse(path, is_train=False)
         config = dict_to_nonedict(config)
         return config
 
     def _download_models(self) -> None:
-        model_dir = pathlib.Path("pretrained_models")
+        model_dir = pathlib.Path('pretrained_models')
         if model_dir.exists():
             return
-        path = huggingface_hub.hf_hub_download("yumingj/Text2Human_SSHQ", "pretrained_models.zip")
+        token = os.getenv('HF_TOKEN')
+        path = huggingface_hub.hf_hub_download('hysts/Text2Human',
+                                               'orig/pretrained_models.zip',
+                                               use_auth_token=token)
         model_dir.mkdir()
         with zipfile.ZipFile(path) as f:
             f.extractall(model_dir)
 
     @staticmethod
     def preprocess_pose_image(image: PIL.Image.Image) -> torch.Tensor:
-        image = (
-            np.array(image.resize(size=(256, 512), resample=PIL.Image.Resampling.LANCZOS))[:, :, 2:]
-            .transpose(2, 0, 1)
-            .astype(np.float32)
-        )
-        image = image / 12.0 - 1
+        logger.debug(f'{image.size=}')
+        image = np.array(
+            image.resize(
+                size=(256, 512),
+                resample=PIL.Image.Resampling.LANCZOS))[:, :, 2:].transpose(
+                    2, 0, 1).astype(np.float32)
+        image = image / 12. - 1
         data = torch.from_numpy(image).unsqueeze(1)
         return data
 
     @staticmethod
     def process_mask(mask: np.ndarray) -> np.ndarray:
+        logger.debug(f'{mask.shape=}')
         if mask.shape != (512, 256, 3):
             return None
+        colors = np.unique(mask.reshape(-1, 3), axis=0)
+        colors = set(map(tuple, colors.tolist()))
+        logger.debug(f'{colors=}')
+        logger.debug(f'{colors - set(COLOR_LIST)=}')
+
         seg_map = np.full(mask.shape[:-1], -1)
         for index, color in enumerate(COLOR_LIST):
             seg_map[np.sum(mask == color, axis=2) == 3] = index
@@ -105,9 +128,11 @@ class Model:
         self.model.feed_pose_data(data)
         return data
 
-    def generate_label_image(self, pose_data: torch.Tensor, shape_text: str) -> np.ndarray:
+    def generate_label_image(self, pose_data: torch.Tensor,
+                             shape_text: str) -> np.ndarray:
         if pose_data is None:
             return
+        logger.debug(f'{len(shape_text)=}')
         self.model.feed_pose_data(pose_data)
         shape_attributes = generate_shape_attributes(shape_text)
         shape_attributes = torch.LongTensor(shape_attributes).unsqueeze(0)
@@ -117,14 +142,18 @@ class Model:
         colored_segm = self.model.palette_result(self.model.segm[0].cpu())
         return colored_segm
 
-    def generate_human(self, label_image: np.ndarray, texture_text: str, sample_steps: int, seed: int) -> np.ndarray:
+    def generate_human(self, label_image: np.ndarray, texture_text: str,
+                       sample_steps: int, seed: int) -> np.ndarray:
         if label_image is None:
             return
+        logger.debug(f'{len(texture_text)=}')
+        logger.debug(f'{sample_steps=}')
         mask = label_image.copy()
         seg_map = self.process_mask(mask)
         if seg_map is None:
             return
-        self.model.segm = torch.from_numpy(seg_map).unsqueeze(0).unsqueeze(0).to(self.model.device)
+        self.model.segm = torch.from_numpy(seg_map).unsqueeze(0).unsqueeze(
+            0).to(self.model.device)
         self.model.generate_quantized_segm()
 
         set_random_seed(seed)

requirements.txt

@@ -1,12 +1,11 @@
-einops==0.6.1
+einops==0.4.1
 lpips==0.1.4
 mmcv-full==1.5.2
 mmsegmentation==0.24.1
-numpy==1.23.5
-openmim==0.1.5
-Pillow==9.5.0
-sentence-transformers==2.2.2
-tokenizers==0.13.3
+numpy==1.22.3
+Pillow==9.1.1
+sentence-transformers==2.2.0
+tokenizers==0.12.1
 torch==1.11.0
 torchvision==0.12.0
-transformers==4.30.2
+transformers==4.19.2

style.css

@@ -1,10 +1,16 @@
 h1 {
   text-align: center;
-  display: block;
 }
 #input-image {
   max-height: 300px;
 }
 #label-image {
-  max-height: 300px;
+  height: 300px;
+}
+#result-image {
+  height: 300px;
+}
+img#visitor-badge {
+  display: block;
+  margin: auto;
 }