Add files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

.pre-commit-config.yaml

@@ -0,0 +1,33 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    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/astral-sh/ruff-pre-commit
+    rev: v0.9.6
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-pytz",
+            "types-PyYAML",
+            "types-requests",
+          ]

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "ms-python.python",
+        "charliermarsh.ruff",
+        "streetsidesoftware.code-spell-checker",
+        "tamasfe.even-better-toml"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,17 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit",
+            "source.organizeImports": "explicit"
+        }
+    },
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "notebook.output.scrolling": true,
+    "notebook.formatOnSave.enabled": true
+}

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 hysts
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,10 +1,10 @@
 ---
 title: DepthPro Transformers
-emoji: 📊
-colorFrom: blue
-colorTo: red
+emoji: ⚡
+colorFrom: red
+colorTo: purple
 sdk: gradio
-sdk_version: 5.16.0
+sdk_version: 4.44.1
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python
+
+import pathlib
+
+import gradio as gr
+import matplotlib as mpl
+import numpy as np
+import PIL.Image
+import spaces
+import torch
+from gradio_imageslider import ImageSlider
+from transformers import DepthProForDepthEstimation, DepthProImageProcessorFast
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+image_processor = DepthProImageProcessorFast.from_pretrained("apple/DepthPro-hf")
+model = DepthProForDepthEstimation.from_pretrained("apple/DepthPro-hf").to(device)
+
+cmap = mpl.colormaps.get_cmap("Spectral_r")
+
+
+@spaces.GPU(duration=10)
+@torch.inference_mode()
+def run(image: PIL.Image.Image) -> tuple[tuple[PIL.Image.Image, PIL.Image.Image], str, str, str, str]:
+    inputs = image_processor(images=image, return_tensors="pt").to(device)
+    outputs = model(**inputs)
+    post_processed_output = image_processor.post_process_depth_estimation(
+        outputs,
+        target_sizes=[(image.height, image.width)],
+    )
+    depth_raw = post_processed_output[0]["predicted_depth"]
+    depth_min = depth_raw.min().item()
+    depth_max = depth_raw.max().item()
+
+    inverse_depth = 1 / depth_raw
+
+    normalized_inverse_depth = (inverse_depth - inverse_depth.min()) / (inverse_depth.max() - inverse_depth.min())
+    normalized_inverse_depth = normalized_inverse_depth * 255.0
+    normalized_inverse_depth = normalized_inverse_depth.detach().cpu().numpy()
+    normalized_inverse_depth = PIL.Image.fromarray(normalized_inverse_depth.astype("uint8"))
+
+    colored_inverse_depth = PIL.Image.fromarray(
+        (cmap(np.array(normalized_inverse_depth))[:, :, :3] * 255).astype(np.uint8)
+    )
+
+    field_of_view = post_processed_output[0]["field_of_view"].item()
+    focal_length = post_processed_output[0]["focal_length"].item()
+
+    return (
+        (image, colored_inverse_depth),
+        f"{field_of_view:.2f}",
+        f"{focal_length:.2f}",
+        f"{depth_min:.2f}",
+        f"{depth_max:.2f}",
+    )
+
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown("# DepthPro")
+    with gr.Row():
+        with gr.Column():
+            input_image = gr.Image(type="pil")
+            run_button = gr.Button()
+        with gr.Column():
+            output_image = ImageSlider()
+            with gr.Row():
+                output_field_of_view = gr.Textbox(label="Field of View")
+                output_focal_length = gr.Textbox(label="Focal Length")
+                output_depth_min = gr.Textbox(label="Depth Min")
+                output_depth_max = gr.Textbox(label="Depth Max")
+    gr.Examples(
+        examples=sorted(pathlib.Path("images").glob("*.jpg")),
+        inputs=input_image,
+        fn=run,
+        outputs=[
+            output_image,
+            output_field_of_view,
+            output_focal_length,
+            output_depth_min,
+            output_depth_max,
+        ],
+    )
+
+    run_button.click(
+        fn=run,
+        inputs=input_image,
+        outputs=[
+            output_image,
+            output_field_of_view,
+            output_focal_length,
+            output_depth_min,
+            output_depth_max,
+        ],
+    )
+
+if __name__ == "__main__":
+    demo.queue().launch()

pyproject.toml

@@ -0,0 +1,61 @@
+[project]
+name = "depthpro-transformers"
+version = "0.1.0"
+description = ""
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "gradio<5",
+    "gradio-imageslider>=0.0.20",
+    "hf-transfer>=0.1.9",
+    "matplotlib>=3.10.0",
+    "spaces>=0.32.0",
+    "torch==2.4.0",
+    "torchvision>=0.19.0",
+    "transformers",
+]
+
+[tool.ruff]
+line-length = 119
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = [
+    "COM812", # missing-trailing-comma
+    "D203",   # one-blank-line-before-class
+    "D213",   # multi-line-summary-second-line
+    "E501",   # line-too-long
+    "SIM117", # multiple-with-statements
+]
+extend-ignore = [
+    "D100",    # undocumented-public-module
+    "D101",    # undocumented-public-class
+    "D102",    # undocumented-public-method
+    "D103",    # undocumented-public-function
+    "D104",    # undocumented-public-package
+    "D105",    # undocumented-magic-method
+    "D107",    # undocumented-public-init
+    "EM101",   # raw-string-in-exception
+    "FBT001",  # boolean-type-hint-positional-argument
+    "FBT002",  # boolean-default-value-positional-argument
+    "PD901",   # pandas-df-variable-name
+    "PGH003",  # blanket-type-ignore
+    "PLR0913", # too-many-arguments
+    "PLR0915", # too-many-statements
+    "TRY003",  # raise-vanilla-args
+]
+unfixable = [
+    "F401", # unused-import
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.per-file-ignores]
+"*.ipynb" = ["T201"]
+
+[tool.ruff.format]
+docstring-code-format = true
+
+[tool.uv.sources]
+transformers = { git = "https://github.com/huggingface/transformers" }

requirements.txt

@@ -0,0 +1,258 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+aiofiles==23.2.1
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.8.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+certifi==2025.1.31
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.1
+    # via requests
+click==8.1.8
+    # via
+    #   typer
+    #   uvicorn
+contourpy==1.3.1
+    # via matplotlib
+cycler==0.12.1
+    # via matplotlib
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.8
+    # via gradio
+ffmpy==0.5.0
+    # via gradio
+filelock==3.17.0
+    # via
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+fonttools==4.56.0
+    # via matplotlib
+fsspec==2025.2.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+gradio==4.44.1
+    # via
+    #   depthpro-transformers (pyproject.toml)
+    #   gradio-imageslider
+    #   spaces
+gradio-client==1.3.0
+    # via gradio
+gradio-imageslider==0.0.20
+    # via depthpro-transformers (pyproject.toml)
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.9
+    # via depthpro-transformers (pyproject.toml)
+httpcore==1.0.7
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   spaces
+huggingface-hub==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+importlib-resources==6.5.2
+    # via gradio
+jinja2==3.1.5
+    # via
+    #   gradio
+    #   torch
+kiwisolver==1.4.8
+    # via matplotlib
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+matplotlib==3.10.0
+    # via
+    #   depthpro-transformers (pyproject.toml)
+    #   gradio
+mdurl==0.1.2
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+networkx==3.4.2
+    # via torch
+numpy==2.2.3
+    # via
+    #   contourpy
+    #   gradio
+    #   matplotlib
+    #   pandas
+    #   torchvision
+    #   transformers
+nvidia-cublas-cu12==12.1.3.1
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.1.105
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.1.105
+    # via torch
+nvidia-cuda-runtime-cu12==12.1.105
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.0.2.54
+    # via torch
+nvidia-curand-cu12==10.3.2.106
+    # via torch
+nvidia-cusolver-cu12==11.4.5.107
+    # via torch
+nvidia-cusparse-cu12==12.1.0.106
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-nccl-cu12==2.20.5
+    # via torch
+nvidia-nvjitlink-cu12==12.8.61
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+nvidia-nvtx-cu12==12.1.105
+    # via torch
+orjson==3.10.15
+    # via gradio
+packaging==24.2
+    # via
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   matplotlib
+    #   spaces
+    #   transformers
+pandas==2.2.3
+    # via gradio
+pillow==10.4.0
+    # via
+    #   gradio
+    #   gradio-imageslider
+    #   matplotlib
+    #   torchvision
+psutil==5.9.8
+    # via spaces
+pydantic==2.10.6
+    # via
+    #   fastapi
+    #   gradio
+    #   spaces
+pydantic-core==2.27.2
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.19.1
+    # via rich
+pyparsing==3.2.1
+    # via matplotlib
+python-dateutil==2.9.0.post0
+    # via
+    #   matplotlib
+    #   pandas
+python-multipart==0.0.20
+    # via gradio
+pytz==2025.1
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+regex==2024.11.6
+    # via transformers
+requests==2.32.3
+    # via
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+rich==13.9.4
+    # via typer
+ruff==0.9.6
+    # via gradio
+safetensors==0.5.2
+    # via transformers
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via anyio
+spaces==0.32.0
+    # via depthpro-transformers (pyproject.toml)
+starlette==0.45.3
+    # via fastapi
+sympy==1.13.3
+    # via torch
+tokenizers==0.21.0
+    # via transformers
+tomlkit==0.12.0
+    # via gradio
+torch==2.4.0
+    # via
+    #   depthpro-transformers (pyproject.toml)
+    #   torchvision
+torchvision==0.19.0
+    # via depthpro-transformers (pyproject.toml)
+tqdm==4.67.1
+    # via
+    #   huggingface-hub
+    #   transformers
+transformers @ git+https://github.com/huggingface/transformers@336dc69d63d56f232a183a3e7f52790429b871ef
+    # via depthpro-transformers (pyproject.toml)
+triton==3.0.0
+    # via torch
+typer==0.15.1
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+    #   rich
+    #   spaces
+    #   torch
+    #   typer
+    #   uvicorn
+tzdata==2025.1
+    # via pandas
+urllib3==2.3.0
+    # via
+    #   gradio
+    #   requests
+uvicorn==0.34.0
+    # via gradio
+websockets==12.0
+    # via gradio-client

style.css

@@ -0,0 +1,11 @@
+h1 {
+  text-align: center;
+  display: block;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}