diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..693c74478b0382cc535d0e2a6747bfcdbd353171 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,27 @@ 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 +Depth-Anything-V2/assets/DA-2K.png filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples_video/basketball.mp4 filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples_video/ferris_wheel.mp4 filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo01.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo02.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo03.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo04.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo05.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo06.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo07.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo08.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo09.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo10.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo11.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo12.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo13.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo14.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo15.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo16.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo17.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo18.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo19.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/examples/demo20.jpg filter=lfs diff=lfs merge=lfs -text +Depth-Anything-V2/assets/teaser.png filter=lfs diff=lfs merge=lfs -text diff --git a/Depth-Anything-V2/.gitattributes b/Depth-Anything-V2/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..50a082dcd8d1996a968e6f5b59c3baf51694d971 --- /dev/null +++ b/Depth-Anything-V2/.gitattributes @@ -0,0 +1,43 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +examples/demo19.jpg filter=lfs diff=lfs merge=lfs -text +assets/DA-2K.png filter=lfs diff=lfs merge=lfs -text +assets/examples_video/basketball.mp4 filter=lfs diff=lfs merge=lfs -text +assets/examples_video/ferris_wheel.mp4 filter=lfs diff=lfs merge=lfs -text +assets/examples/demo19.jpg filter=lfs diff=lfs merge=lfs -text +assets/teaser.png filter=lfs diff=lfs merge=lfs -text +metric_depth/assets/compare_zoedepth.png filter=lfs diff=lfs merge=lfs -text +metric_depth/dataset/splits/hypersim/train.txt filter=lfs diff=lfs merge=lfs -text diff --git a/Depth-Anything-V2/README.md b/Depth-Anything-V2/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a06c6645b6eddbd191e75e838e883238fcc11e40 --- /dev/null +++ b/Depth-Anything-V2/README.md @@ -0,0 +1,13 @@ +--- +title: Depth Anything V2 +emoji: 🌖 +colorFrom: red +colorTo: indigo +sdk: gradio +sdk_version: 4.36.0 +app_file: app.py +pinned: false +license: apache-2.0 +--- + +Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference \ No newline at end of file diff --git a/Depth-Anything-V2/app.py b/Depth-Anything-V2/app.py new file mode 100644 index 0000000000000000000000000000000000000000..393cc5497ac37d64de9ad542ea0567e0739e6493 --- /dev/null +++ b/Depth-Anything-V2/app.py @@ -0,0 +1,102 @@ +import gradio as gr +import cv2 +import matplotlib +import numpy as np +import os +from PIL import Image +import spaces +import torch +import tempfile +from gradio_imageslider import ImageSlider +from huggingface_hub import hf_hub_download + +from depth_anything_v2.dpt import DepthAnythingV2 + +css = """ +#img-display-container { + max-height: 100vh; +} +#img-display-input { + max-height: 80vh; +} +#img-display-output { + max-height: 80vh; +} +#download { + height: 62px; +} +""" +DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu' +model_configs = { + 'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384]}, + 'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768]}, + 'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024]}, + 'vitg': {'encoder': 'vitg', 'features': 384, 'out_channels': [1536, 1536, 1536, 1536]} +} +encoder2name = { + 'vits': 'Small', + 'vitb': 'Base', + 'vitl': 'Large', + 'vitg': 'Giant', # we are undergoing company review procedures to release our giant model checkpoint +} +encoder = 'vitl' +model_name = encoder2name[encoder] +model = DepthAnythingV2(**model_configs[encoder]) +filepath = hf_hub_download(repo_id=f"depth-anything/Depth-Anything-V2-{model_name}", filename=f"depth_anything_v2_{encoder}.pth", repo_type="model") +state_dict = torch.load(filepath, map_location="cpu") +model.load_state_dict(state_dict) +model = model.to(DEVICE).eval() + +title = "# Depth Anything V2" +description = """Official demo for **Depth Anything V2**. +Please refer to our [paper](https://arxiv.org/abs/2406.09414), [project page](https://depth-anything-v2.github.io), and [github](https://github.com/DepthAnything/Depth-Anything-V2) for more details.""" + +@spaces.GPU +def predict_depth(image): + return model.infer_image(image) + +with gr.Blocks(css=css) as demo: + gr.Markdown(title) + gr.Markdown(description) + gr.Markdown("### Depth Prediction demo") + + with gr.Row(): + input_image = gr.Image(label="Input Image", type='numpy', elem_id='img-display-input') + depth_image_slider = ImageSlider(label="Depth Map with Slider View", elem_id='img-display-output', position=0.5) + submit = gr.Button(value="Compute Depth") + gray_depth_file = gr.File(label="Grayscale depth map", elem_id="download",) + raw_file = gr.File(label="16-bit raw output (can be considered as disparity)", elem_id="download",) + + cmap = matplotlib.colormaps.get_cmap('Spectral_r') + + def on_submit(image): + original_image = image.copy() + + h, w = image.shape[:2] + + depth = predict_depth(image[:, :, ::-1]) + + raw_depth = Image.fromarray(depth.astype('uint16')) + tmp_raw_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False) + raw_depth.save(tmp_raw_depth.name) + + depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0 + depth = depth.astype(np.uint8) + colored_depth = (cmap(depth)[:, :, :3] * 255).astype(np.uint8) + + gray_depth = Image.fromarray(depth) + tmp_gray_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False) + gray_depth.save(tmp_gray_depth.name) + + return [(original_image, colored_depth), tmp_gray_depth.name, tmp_raw_depth.name] + + submit.click(on_submit, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file]) + + example_files = os.listdir('assets/examples') + example_files.sort() + example_files = [os.path.join('assets/examples', filename) for filename in example_files] + examples = gr.Examples(examples=example_files, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file], fn=on_submit) + + +if __name__ == '__main__': + demo.queue().launch(share=True) diff --git a/Depth-Anything-V2/assets/DA-2K.png b/Depth-Anything-V2/assets/DA-2K.png new file mode 100644 index 0000000000000000000000000000000000000000..e1de051f8f6e801054bc6853c17ed2edd99de186 --- /dev/null +++ b/Depth-Anything-V2/assets/DA-2K.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5aa376424bfc2dfdfa140773690d85b22b51200dc0b02324beb050de9b51d69 +size 1180754 diff --git a/Depth-Anything-V2/assets/examples/demo01.jpg b/Depth-Anything-V2/assets/examples/demo01.jpg new file mode 100644 index 0000000000000000000000000000000000000000..52f8b3155e90b44bc59d1072f30821a1c63366fe --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo01.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ef1bbb63f6540e49aa9b6302b9b938be4fe8b9c08c07c3694b02396b0e87e0 +size 488150 diff --git a/Depth-Anything-V2/assets/examples/demo02.jpg b/Depth-Anything-V2/assets/examples/demo02.jpg new file mode 100644 index 0000000000000000000000000000000000000000..2953bdff7db4ef271bfe1fc7d588b0063eebfe63 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo02.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f116034aa5abd5b5470226be2bb03bd938c8affe90389c52d10fe8b1ac7e21 +size 510806 diff --git a/Depth-Anything-V2/assets/examples/demo03.jpg b/Depth-Anything-V2/assets/examples/demo03.jpg new file mode 100644 index 0000000000000000000000000000000000000000..bbe4590abdd0988b242505a8863fe10b60056e5e --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo03.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:764dffd4d97bbacd620bc005fa86837018393ccb5ffd1059c2245a3cacff7782 +size 464937 diff --git a/Depth-Anything-V2/assets/examples/demo04.jpg b/Depth-Anything-V2/assets/examples/demo04.jpg new file mode 100644 index 0000000000000000000000000000000000000000..f8cd0dc713353af5dc56404a2c8b50adc7eae5fb --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo04.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a301f4e0361fe75ca4d256a35062f87eecc3f7655d747c9def3259c86e26a45 +size 299824 diff --git a/Depth-Anything-V2/assets/examples/demo05.jpg b/Depth-Anything-V2/assets/examples/demo05.jpg new file mode 100644 index 0000000000000000000000000000000000000000..72da79f211e06ee7e1c736290c01c4d251e83f77 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo05.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50e7e2f057c5a2d27bb09b0b3e814147966e30139ddaf54362c72746a5320339 +size 353184 diff --git a/Depth-Anything-V2/assets/examples/demo06.jpg b/Depth-Anything-V2/assets/examples/demo06.jpg new file mode 100644 index 0000000000000000000000000000000000000000..ac7991e6a09dee7f77ef32b846b19582ddd05001 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo06.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd815bddeab139e7477c948a22fffdf84d9b87f81d77dcf6fd8ef39ebaaafb5 +size 782780 diff --git a/Depth-Anything-V2/assets/examples/demo07.jpg b/Depth-Anything-V2/assets/examples/demo07.jpg new file mode 100644 index 0000000000000000000000000000000000000000..54412b758b1101bda0e2ba7156eadd9cc8fa704a --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo07.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345bec735adc4c238bf14ddf1d182c4881f8ba08814c4f4074c1d79e9e4adc52 +size 400463 diff --git a/Depth-Anything-V2/assets/examples/demo08.jpg b/Depth-Anything-V2/assets/examples/demo08.jpg new file mode 100644 index 0000000000000000000000000000000000000000..33b96480686055a03ce961705586b2ec886ac116 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo08.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32b480349013be5f84521b0df1d6590139163aef8457f051076ed03c7371e6f +size 102825 diff --git a/Depth-Anything-V2/assets/examples/demo09.jpg b/Depth-Anything-V2/assets/examples/demo09.jpg new file mode 100644 index 0000000000000000000000000000000000000000..f5e37daa0fc7d423f2ede3459f710f691cb76ccd --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo09.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a64033ba69bb408c092dbff811abfbcb0196f1f87541902d03d2a909a0b8ea9 +size 410224 diff --git a/Depth-Anything-V2/assets/examples/demo10.jpg b/Depth-Anything-V2/assets/examples/demo10.jpg new file mode 100644 index 0000000000000000000000000000000000000000..5ef93300c63e39115bdaa3486dffd8671f429d6c --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo10.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc77f215081f58de8d079e821e2808f6ee2727dfa729c10a5921c186a32c7638 +size 486825 diff --git a/Depth-Anything-V2/assets/examples/demo11.jpg b/Depth-Anything-V2/assets/examples/demo11.jpg new file mode 100644 index 0000000000000000000000000000000000000000..601c84aca838494ec14b740a85044d937e782c43 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo11.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150ef98e997ee6ff705bd06105c343f76a8f181ef93ff9ceebbd62a3ab6b592b +size 243712 diff --git a/Depth-Anything-V2/assets/examples/demo12.jpg b/Depth-Anything-V2/assets/examples/demo12.jpg new file mode 100644 index 0000000000000000000000000000000000000000..9a1c4f8a489bf721c860e664d90d9fbb5f5dbacf --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo12.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264458adcf5af6e3733dfda7ef4628c4a1dc49ed249aa8896256d9534a8377c4 +size 263007 diff --git a/Depth-Anything-V2/assets/examples/demo13.jpg b/Depth-Anything-V2/assets/examples/demo13.jpg new file mode 100644 index 0000000000000000000000000000000000000000..e9b392d78128e9a34b23cf7d852eaf8a94681f0d --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo13.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9168fc752a002d50138a56621e8de5fab7fed125a978dd293319d28d30993564 +size 421112 diff --git a/Depth-Anything-V2/assets/examples/demo14.jpg b/Depth-Anything-V2/assets/examples/demo14.jpg new file mode 100644 index 0000000000000000000000000000000000000000..b44ca7975a65f70c3ddbfe413be6ec86abda2005 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo14.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01480d952bc950332f0eea31da0777f66d5f285d8edfe2a5f47508f4b260a99f +size 642925 diff --git a/Depth-Anything-V2/assets/examples/demo15.jpg b/Depth-Anything-V2/assets/examples/demo15.jpg new file mode 100644 index 0000000000000000000000000000000000000000..25d35f0d4df7d57e32e9d885afb7d5d127dd6dd3 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo15.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf60ce3879f627e8886280cc61442174c91908894a5b059681341fed600f7db3 +size 768703 diff --git a/Depth-Anything-V2/assets/examples/demo16.jpg b/Depth-Anything-V2/assets/examples/demo16.jpg new file mode 100644 index 0000000000000000000000000000000000000000..16f7009cf051e3da4f73987e1d5ae2bc9d02e1ad --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo16.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92e51732b38ad8b21b5cbbc6883374bd5ab56bb4907d6c4f1e13307970480ee +size 377831 diff --git a/Depth-Anything-V2/assets/examples/demo17.jpg b/Depth-Anything-V2/assets/examples/demo17.jpg new file mode 100644 index 0000000000000000000000000000000000000000..61b18cac78a257b347124dc7e9164d3aa4047cb8 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo17.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7174dcfbbb95a2e581ebf1e14cfbb4bef7a1295ae9cece405c87145223dcb32d +size 152591 diff --git a/Depth-Anything-V2/assets/examples/demo18.jpg b/Depth-Anything-V2/assets/examples/demo18.jpg new file mode 100644 index 0000000000000000000000000000000000000000..0ed634012d3f6d320dd6a61d7bf7b5c555b25d8d --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo18.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4deeb16dbee40108f194bd87c8621416110427c8ab5fc5ad6a1d9002b2b620c2 +size 178905 diff --git a/Depth-Anything-V2/assets/examples/demo19.jpg b/Depth-Anything-V2/assets/examples/demo19.jpg new file mode 100644 index 0000000000000000000000000000000000000000..6213ae1151e010f57ce7bd48648b3ee7e7039ebe --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo19.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cdb09c34eb0b4d2ac5f6070aec47c8f983a0b1b2c9ee1fc30decafb64f1bd98 +size 1004211 diff --git a/Depth-Anything-V2/assets/examples/demo20.jpg b/Depth-Anything-V2/assets/examples/demo20.jpg new file mode 100644 index 0000000000000000000000000000000000000000..88237b85c7ba6b7b00f83cbfe379134a855d8f58 --- /dev/null +++ b/Depth-Anything-V2/assets/examples/demo20.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2958fd1b7018e40b68ccc8d74ff8e50bf143f5046711d57c54eec2a479550ace +size 498212 diff --git a/Depth-Anything-V2/assets/examples_video/basketball.mp4 b/Depth-Anything-V2/assets/examples_video/basketball.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ee772a10663b38e21c2b4ab7422b7f595b9a1388 --- /dev/null +++ b/Depth-Anything-V2/assets/examples_video/basketball.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3049687fa169e8383c8f90086ea457bd786e72e85584ec8b511599ebcc6cbb27 +size 9714271 diff --git a/Depth-Anything-V2/assets/examples_video/ferris_wheel.mp4 b/Depth-Anything-V2/assets/examples_video/ferris_wheel.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f948fecfb2c10f37fdd503cd75660ef4955c6ae6 --- /dev/null +++ b/Depth-Anything-V2/assets/examples_video/ferris_wheel.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df452351def30bc0be2fef6be57e93745074954755a2b03f2b706045747a9697 +size 5334034 diff --git a/Depth-Anything-V2/assets/teaser.png b/Depth-Anything-V2/assets/teaser.png new file mode 100644 index 0000000000000000000000000000000000000000..27c1cc626a4c636b6f3ac60f126c6c065ce2aee4 --- /dev/null +++ b/Depth-Anything-V2/assets/teaser.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5609203ee36b8745303051e474ea02d452595b85698a33d643c5800797402e1 +size 12818034 diff --git a/Depth-Anything-V2/depth_anything_v2/__pycache__/dinov2.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/__pycache__/dinov2.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a86562b8375d658b511d75f984c1622fc3a99d38 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/__pycache__/dinov2.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/__pycache__/dpt.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/__pycache__/dpt.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f2517b9821f0439e21d35617633786aa815d1d69 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/__pycache__/dpt.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2.py b/Depth-Anything-V2/depth_anything_v2/dinov2.py new file mode 100644 index 0000000000000000000000000000000000000000..5cbfc7d24d37796d5310fd966b582bb3773685dc --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2.py @@ -0,0 +1,415 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# +# This source code is licensed under the Apache License, Version 2.0 +# found in the LICENSE file in the root directory of this source tree. + +# References: +# https://github.com/facebookresearch/dino/blob/main/vision_transformer.py +# https://github.com/rwightman/pytorch-image-models/tree/master/timm/models/vision_transformer.py + +from functools import partial +import math +import logging +from typing import Sequence, Tuple, Union, Callable + +import torch +import torch.nn as nn +import torch.utils.checkpoint +from torch.nn.init import trunc_normal_ + +from .dinov2_layers import Mlp, PatchEmbed, SwiGLUFFNFused, MemEffAttention, NestedTensorBlock as Block + + +logger = logging.getLogger("dinov2") + + +def named_apply(fn: Callable, module: nn.Module, name="", depth_first=True, include_root=False) -> nn.Module: + if not depth_first and include_root: + fn(module=module, name=name) + for child_name, child_module in module.named_children(): + child_name = ".".join((name, child_name)) if name else child_name + named_apply(fn=fn, module=child_module, name=child_name, depth_first=depth_first, include_root=True) + if depth_first and include_root: + fn(module=module, name=name) + return module + + +class BlockChunk(nn.ModuleList): + def forward(self, x): + for b in self: + x = b(x) + return x + + +class DinoVisionTransformer(nn.Module): + def __init__( + self, + img_size=224, + patch_size=16, + in_chans=3, + embed_dim=768, + depth=12, + num_heads=12, + mlp_ratio=4.0, + qkv_bias=True, + ffn_bias=True, + proj_bias=True, + drop_path_rate=0.0, + drop_path_uniform=False, + init_values=None, # for layerscale: None or 0 => no layerscale + embed_layer=PatchEmbed, + act_layer=nn.GELU, + block_fn=Block, + ffn_layer="mlp", + block_chunks=1, + num_register_tokens=0, + interpolate_antialias=False, + interpolate_offset=0.1, + ): + """ + Args: + img_size (int, tuple): input image size + patch_size (int, tuple): patch size + in_chans (int): number of input channels + embed_dim (int): embedding dimension + depth (int): depth of transformer + num_heads (int): number of attention heads + mlp_ratio (int): ratio of mlp hidden dim to embedding dim + qkv_bias (bool): enable bias for qkv if True + proj_bias (bool): enable bias for proj in attn if True + ffn_bias (bool): enable bias for ffn if True + drop_path_rate (float): stochastic depth rate + drop_path_uniform (bool): apply uniform drop rate across blocks + weight_init (str): weight init scheme + init_values (float): layer-scale init values + embed_layer (nn.Module): patch embedding layer + act_layer (nn.Module): MLP activation layer + block_fn (nn.Module): transformer block class + ffn_layer (str): "mlp", "swiglu", "swiglufused" or "identity" + block_chunks: (int) split block sequence into block_chunks units for FSDP wrap + num_register_tokens: (int) number of extra cls tokens (so-called "registers") + interpolate_antialias: (str) flag to apply anti-aliasing when interpolating positional embeddings + interpolate_offset: (float) work-around offset to apply when interpolating positional embeddings + """ + super().__init__() + norm_layer = partial(nn.LayerNorm, eps=1e-6) + + self.num_features = self.embed_dim = embed_dim # num_features for consistency with other models + self.num_tokens = 1 + self.n_blocks = depth + self.num_heads = num_heads + self.patch_size = patch_size + self.num_register_tokens = num_register_tokens + self.interpolate_antialias = interpolate_antialias + self.interpolate_offset = interpolate_offset + + self.patch_embed = embed_layer(img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim) + num_patches = self.patch_embed.num_patches + + self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim)) + self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim)) + assert num_register_tokens >= 0 + self.register_tokens = ( + nn.Parameter(torch.zeros(1, num_register_tokens, embed_dim)) if num_register_tokens else None + ) + + if drop_path_uniform is True: + dpr = [drop_path_rate] * depth + else: + dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)] # stochastic depth decay rule + + if ffn_layer == "mlp": + logger.info("using MLP layer as FFN") + ffn_layer = Mlp + elif ffn_layer == "swiglufused" or ffn_layer == "swiglu": + logger.info("using SwiGLU layer as FFN") + ffn_layer = SwiGLUFFNFused + elif ffn_layer == "identity": + logger.info("using Identity layer as FFN") + + def f(*args, **kwargs): + return nn.Identity() + + ffn_layer = f + else: + raise NotImplementedError + + blocks_list = [ + block_fn( + dim=embed_dim, + num_heads=num_heads, + mlp_ratio=mlp_ratio, + qkv_bias=qkv_bias, + proj_bias=proj_bias, + ffn_bias=ffn_bias, + drop_path=dpr[i], + norm_layer=norm_layer, + act_layer=act_layer, + ffn_layer=ffn_layer, + init_values=init_values, + ) + for i in range(depth) + ] + if block_chunks > 0: + self.chunked_blocks = True + chunked_blocks = [] + chunksize = depth // block_chunks + for i in range(0, depth, chunksize): + # this is to keep the block index consistent if we chunk the block list + chunked_blocks.append([nn.Identity()] * i + blocks_list[i : i + chunksize]) + self.blocks = nn.ModuleList([BlockChunk(p) for p in chunked_blocks]) + else: + self.chunked_blocks = False + self.blocks = nn.ModuleList(blocks_list) + + self.norm = norm_layer(embed_dim) + self.head = nn.Identity() + + self.mask_token = nn.Parameter(torch.zeros(1, embed_dim)) + + self.init_weights() + + def init_weights(self): + trunc_normal_(self.pos_embed, std=0.02) + nn.init.normal_(self.cls_token, std=1e-6) + if self.register_tokens is not None: + nn.init.normal_(self.register_tokens, std=1e-6) + named_apply(init_weights_vit_timm, self) + + def interpolate_pos_encoding(self, x, w, h): + previous_dtype = x.dtype + npatch = x.shape[1] - 1 + N = self.pos_embed.shape[1] - 1 + if npatch == N and w == h: + return self.pos_embed + pos_embed = self.pos_embed.float() + class_pos_embed = pos_embed[:, 0] + patch_pos_embed = pos_embed[:, 1:] + dim = x.shape[-1] + w0 = w // self.patch_size + h0 = h // self.patch_size + # we add a small number to avoid floating point error in the interpolation + # see discussion at https://github.com/facebookresearch/dino/issues/8 + # DINOv2 with register modify the interpolate_offset from 0.1 to 0.0 + w0, h0 = w0 + self.interpolate_offset, h0 + self.interpolate_offset + # w0, h0 = w0 + 0.1, h0 + 0.1 + + sqrt_N = math.sqrt(N) + sx, sy = float(w0) / sqrt_N, float(h0) / sqrt_N + patch_pos_embed = nn.functional.interpolate( + patch_pos_embed.reshape(1, int(sqrt_N), int(sqrt_N), dim).permute(0, 3, 1, 2), + scale_factor=(sx, sy), + # (int(w0), int(h0)), # to solve the upsampling shape issue + mode="bicubic", + antialias=self.interpolate_antialias + ) + + assert int(w0) == patch_pos_embed.shape[-2] + assert int(h0) == patch_pos_embed.shape[-1] + patch_pos_embed = patch_pos_embed.permute(0, 2, 3, 1).view(1, -1, dim) + return torch.cat((class_pos_embed.unsqueeze(0), patch_pos_embed), dim=1).to(previous_dtype) + + def prepare_tokens_with_masks(self, x, masks=None): + B, nc, w, h = x.shape + x = self.patch_embed(x) + if masks is not None: + x = torch.where(masks.unsqueeze(-1), self.mask_token.to(x.dtype).unsqueeze(0), x) + + x = torch.cat((self.cls_token.expand(x.shape[0], -1, -1), x), dim=1) + x = x + self.interpolate_pos_encoding(x, w, h) + + if self.register_tokens is not None: + x = torch.cat( + ( + x[:, :1], + self.register_tokens.expand(x.shape[0], -1, -1), + x[:, 1:], + ), + dim=1, + ) + + return x + + def forward_features_list(self, x_list, masks_list): + x = [self.prepare_tokens_with_masks(x, masks) for x, masks in zip(x_list, masks_list)] + for blk in self.blocks: + x = blk(x) + + all_x = x + output = [] + for x, masks in zip(all_x, masks_list): + x_norm = self.norm(x) + output.append( + { + "x_norm_clstoken": x_norm[:, 0], + "x_norm_regtokens": x_norm[:, 1 : self.num_register_tokens + 1], + "x_norm_patchtokens": x_norm[:, self.num_register_tokens + 1 :], + "x_prenorm": x, + "masks": masks, + } + ) + return output + + def forward_features(self, x, masks=None): + if isinstance(x, list): + return self.forward_features_list(x, masks) + + x = self.prepare_tokens_with_masks(x, masks) + + for blk in self.blocks: + x = blk(x) + + x_norm = self.norm(x) + return { + "x_norm_clstoken": x_norm[:, 0], + "x_norm_regtokens": x_norm[:, 1 : self.num_register_tokens + 1], + "x_norm_patchtokens": x_norm[:, self.num_register_tokens + 1 :], + "x_prenorm": x, + "masks": masks, + } + + def _get_intermediate_layers_not_chunked(self, x, n=1): + x = self.prepare_tokens_with_masks(x) + # If n is an int, take the n last blocks. If it's a list, take them + output, total_block_len = [], len(self.blocks) + blocks_to_take = range(total_block_len - n, total_block_len) if isinstance(n, int) else n + for i, blk in enumerate(self.blocks): + x = blk(x) + if i in blocks_to_take: + output.append(x) + assert len(output) == len(blocks_to_take), f"only {len(output)} / {len(blocks_to_take)} blocks found" + return output + + def _get_intermediate_layers_chunked(self, x, n=1): + x = self.prepare_tokens_with_masks(x) + output, i, total_block_len = [], 0, len(self.blocks[-1]) + # If n is an int, take the n last blocks. If it's a list, take them + blocks_to_take = range(total_block_len - n, total_block_len) if isinstance(n, int) else n + for block_chunk in self.blocks: + for blk in block_chunk[i:]: # Passing the nn.Identity() + x = blk(x) + if i in blocks_to_take: + output.append(x) + i += 1 + assert len(output) == len(blocks_to_take), f"only {len(output)} / {len(blocks_to_take)} blocks found" + return output + + def get_intermediate_layers( + self, + x: torch.Tensor, + n: Union[int, Sequence] = 1, # Layers or n last layers to take + reshape: bool = False, + return_class_token: bool = False, + norm=True + ) -> Tuple[Union[torch.Tensor, Tuple[torch.Tensor]]]: + if self.chunked_blocks: + outputs = self._get_intermediate_layers_chunked(x, n) + else: + outputs = self._get_intermediate_layers_not_chunked(x, n) + if norm: + outputs = [self.norm(out) for out in outputs] + class_tokens = [out[:, 0] for out in outputs] + outputs = [out[:, 1 + self.num_register_tokens:] for out in outputs] + if reshape: + B, _, w, h = x.shape + outputs = [ + out.reshape(B, w // self.patch_size, h // self.patch_size, -1).permute(0, 3, 1, 2).contiguous() + for out in outputs + ] + if return_class_token: + return tuple(zip(outputs, class_tokens)) + return tuple(outputs) + + def forward(self, *args, is_training=False, **kwargs): + ret = self.forward_features(*args, **kwargs) + if is_training: + return ret + else: + return self.head(ret["x_norm_clstoken"]) + + +def init_weights_vit_timm(module: nn.Module, name: str = ""): + """ViT weight initialization, original timm impl (for reproducibility)""" + if isinstance(module, nn.Linear): + trunc_normal_(module.weight, std=0.02) + if module.bias is not None: + nn.init.zeros_(module.bias) + + +def vit_small(patch_size=16, num_register_tokens=0, **kwargs): + model = DinoVisionTransformer( + patch_size=patch_size, + embed_dim=384, + depth=12, + num_heads=6, + mlp_ratio=4, + block_fn=partial(Block, attn_class=MemEffAttention), + num_register_tokens=num_register_tokens, + **kwargs, + ) + return model + + +def vit_base(patch_size=16, num_register_tokens=0, **kwargs): + model = DinoVisionTransformer( + patch_size=patch_size, + embed_dim=768, + depth=12, + num_heads=12, + mlp_ratio=4, + block_fn=partial(Block, attn_class=MemEffAttention), + num_register_tokens=num_register_tokens, + **kwargs, + ) + return model + + +def vit_large(patch_size=16, num_register_tokens=0, **kwargs): + model = DinoVisionTransformer( + patch_size=patch_size, + embed_dim=1024, + depth=24, + num_heads=16, + mlp_ratio=4, + block_fn=partial(Block, attn_class=MemEffAttention), + num_register_tokens=num_register_tokens, + **kwargs, + ) + return model + + +def vit_giant2(patch_size=16, num_register_tokens=0, **kwargs): + """ + Close to ViT-giant, with embed-dim 1536 and 24 heads => embed-dim per head 64 + """ + model = DinoVisionTransformer( + patch_size=patch_size, + embed_dim=1536, + depth=40, + num_heads=24, + mlp_ratio=4, + block_fn=partial(Block, attn_class=MemEffAttention), + num_register_tokens=num_register_tokens, + **kwargs, + ) + return model + + +def DINOv2(model_name): + model_zoo = { + "vits": vit_small, + "vitb": vit_base, + "vitl": vit_large, + "vitg": vit_giant2 + } + + return model_zoo[model_name]( + img_size=518, + patch_size=14, + init_values=1.0, + ffn_layer="mlp" if model_name != "vitg" else "swiglufused", + block_chunks=0, + num_register_tokens=0, + interpolate_antialias=False, + interpolate_offset=0.1 + ) diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__init__.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e59a83eb90512d763b03e4d38536b6ae07e87541 --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__init__.py @@ -0,0 +1,11 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +from .mlp import Mlp +from .patch_embed import PatchEmbed +from .swiglu_ffn import SwiGLUFFN, SwiGLUFFNFused +from .block import NestedTensorBlock +from .attention import MemEffAttention diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/__init__.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9a57544eee11e1fbd2628db3e4aa34cfe33c35fb Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/__init__.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/attention.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/attention.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3f2c22d19d72ea965074f7e2495c872b52e4ac6e Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/attention.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/block.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/block.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..237ee93c61642d1ea067995caec6bb99b6e06678 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/block.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/drop_path.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/drop_path.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1341fa096a0b1a8f4ca59f60a59b522f2bbb4354 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/drop_path.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/layer_scale.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/layer_scale.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..611eba42e3421fc0a59f77deb05fa5c2a3d75bb8 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/layer_scale.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/mlp.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/mlp.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4ed30bdd7926a7290a0b9265a6659b4bf2cf74d4 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/mlp.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/patch_embed.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/patch_embed.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..beaee11cb1480f3b71609e15666fa125169d3174 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/patch_embed.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/swiglu_ffn.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/swiglu_ffn.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fdedc006acec035153a18279beb5e3810387ec96 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/__pycache__/swiglu_ffn.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/attention.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/attention.py new file mode 100644 index 0000000000000000000000000000000000000000..dea0c82d55f052bf4bcb5896ad8c37158ef523d5 --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/attention.py @@ -0,0 +1,83 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +# References: +# https://github.com/facebookresearch/dino/blob/master/vision_transformer.py +# https://github.com/rwightman/pytorch-image-models/tree/master/timm/models/vision_transformer.py + +import logging + +from torch import Tensor +from torch import nn + + +logger = logging.getLogger("dinov2") + + +try: + from xformers.ops import memory_efficient_attention, unbind, fmha + + XFORMERS_AVAILABLE = True +except ImportError: + logger.warning("xFormers not available") + XFORMERS_AVAILABLE = False + + +class Attention(nn.Module): + def __init__( + self, + dim: int, + num_heads: int = 8, + qkv_bias: bool = False, + proj_bias: bool = True, + attn_drop: float = 0.0, + proj_drop: float = 0.0, + ) -> None: + super().__init__() + self.num_heads = num_heads + head_dim = dim // num_heads + self.scale = head_dim**-0.5 + + self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias) + self.attn_drop = nn.Dropout(attn_drop) + self.proj = nn.Linear(dim, dim, bias=proj_bias) + self.proj_drop = nn.Dropout(proj_drop) + + def forward(self, x: Tensor) -> Tensor: + B, N, C = x.shape + qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4) + + q, k, v = qkv[0] * self.scale, qkv[1], qkv[2] + attn = q @ k.transpose(-2, -1) + + attn = attn.softmax(dim=-1) + attn = self.attn_drop(attn) + + x = (attn @ v).transpose(1, 2).reshape(B, N, C) + x = self.proj(x) + x = self.proj_drop(x) + return x + + +class MemEffAttention(Attention): + def forward(self, x: Tensor, attn_bias=None) -> Tensor: + if not XFORMERS_AVAILABLE: + assert attn_bias is None, "xFormers is required for nested tensors usage" + return super().forward(x) + + B, N, C = x.shape + qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads) + + q, k, v = unbind(qkv, 2) + + x = memory_efficient_attention(q, k, v, attn_bias=attn_bias) + x = x.reshape([B, N, C]) + + x = self.proj(x) + x = self.proj_drop(x) + return x + + \ No newline at end of file diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/block.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/block.py new file mode 100644 index 0000000000000000000000000000000000000000..f91f3f07bd15fba91c67068c8dce2bb22d505bf7 --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/block.py @@ -0,0 +1,252 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +# References: +# https://github.com/facebookresearch/dino/blob/master/vision_transformer.py +# https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/patch_embed.py + +import logging +from typing import Callable, List, Any, Tuple, Dict + +import torch +from torch import nn, Tensor + +from .attention import Attention, MemEffAttention +from .drop_path import DropPath +from .layer_scale import LayerScale +from .mlp import Mlp + + +logger = logging.getLogger("dinov2") + + +try: + from xformers.ops import fmha + from xformers.ops import scaled_index_add, index_select_cat + + XFORMERS_AVAILABLE = True +except ImportError: + logger.warning("xFormers not available") + XFORMERS_AVAILABLE = False + + +class Block(nn.Module): + def __init__( + self, + dim: int, + num_heads: int, + mlp_ratio: float = 4.0, + qkv_bias: bool = False, + proj_bias: bool = True, + ffn_bias: bool = True, + drop: float = 0.0, + attn_drop: float = 0.0, + init_values=None, + drop_path: float = 0.0, + act_layer: Callable[..., nn.Module] = nn.GELU, + norm_layer: Callable[..., nn.Module] = nn.LayerNorm, + attn_class: Callable[..., nn.Module] = Attention, + ffn_layer: Callable[..., nn.Module] = Mlp, + ) -> None: + super().__init__() + # print(f"biases: qkv: {qkv_bias}, proj: {proj_bias}, ffn: {ffn_bias}") + self.norm1 = norm_layer(dim) + self.attn = attn_class( + dim, + num_heads=num_heads, + qkv_bias=qkv_bias, + proj_bias=proj_bias, + attn_drop=attn_drop, + proj_drop=drop, + ) + self.ls1 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity() + self.drop_path1 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity() + + self.norm2 = norm_layer(dim) + mlp_hidden_dim = int(dim * mlp_ratio) + self.mlp = ffn_layer( + in_features=dim, + hidden_features=mlp_hidden_dim, + act_layer=act_layer, + drop=drop, + bias=ffn_bias, + ) + self.ls2 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity() + self.drop_path2 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity() + + self.sample_drop_ratio = drop_path + + def forward(self, x: Tensor) -> Tensor: + def attn_residual_func(x: Tensor) -> Tensor: + return self.ls1(self.attn(self.norm1(x))) + + def ffn_residual_func(x: Tensor) -> Tensor: + return self.ls2(self.mlp(self.norm2(x))) + + if self.training and self.sample_drop_ratio > 0.1: + # the overhead is compensated only for a drop path rate larger than 0.1 + x = drop_add_residual_stochastic_depth( + x, + residual_func=attn_residual_func, + sample_drop_ratio=self.sample_drop_ratio, + ) + x = drop_add_residual_stochastic_depth( + x, + residual_func=ffn_residual_func, + sample_drop_ratio=self.sample_drop_ratio, + ) + elif self.training and self.sample_drop_ratio > 0.0: + x = x + self.drop_path1(attn_residual_func(x)) + x = x + self.drop_path1(ffn_residual_func(x)) # FIXME: drop_path2 + else: + x = x + attn_residual_func(x) + x = x + ffn_residual_func(x) + return x + + +def drop_add_residual_stochastic_depth( + x: Tensor, + residual_func: Callable[[Tensor], Tensor], + sample_drop_ratio: float = 0.0, +) -> Tensor: + # 1) extract subset using permutation + b, n, d = x.shape + sample_subset_size = max(int(b * (1 - sample_drop_ratio)), 1) + brange = (torch.randperm(b, device=x.device))[:sample_subset_size] + x_subset = x[brange] + + # 2) apply residual_func to get residual + residual = residual_func(x_subset) + + x_flat = x.flatten(1) + residual = residual.flatten(1) + + residual_scale_factor = b / sample_subset_size + + # 3) add the residual + x_plus_residual = torch.index_add(x_flat, 0, brange, residual.to(dtype=x.dtype), alpha=residual_scale_factor) + return x_plus_residual.view_as(x) + + +def get_branges_scales(x, sample_drop_ratio=0.0): + b, n, d = x.shape + sample_subset_size = max(int(b * (1 - sample_drop_ratio)), 1) + brange = (torch.randperm(b, device=x.device))[:sample_subset_size] + residual_scale_factor = b / sample_subset_size + return brange, residual_scale_factor + + +def add_residual(x, brange, residual, residual_scale_factor, scaling_vector=None): + if scaling_vector is None: + x_flat = x.flatten(1) + residual = residual.flatten(1) + x_plus_residual = torch.index_add(x_flat, 0, brange, residual.to(dtype=x.dtype), alpha=residual_scale_factor) + else: + x_plus_residual = scaled_index_add( + x, brange, residual.to(dtype=x.dtype), scaling=scaling_vector, alpha=residual_scale_factor + ) + return x_plus_residual + + +attn_bias_cache: Dict[Tuple, Any] = {} + + +def get_attn_bias_and_cat(x_list, branges=None): + """ + this will perform the index select, cat the tensors, and provide the attn_bias from cache + """ + batch_sizes = [b.shape[0] for b in branges] if branges is not None else [x.shape[0] for x in x_list] + all_shapes = tuple((b, x.shape[1]) for b, x in zip(batch_sizes, x_list)) + if all_shapes not in attn_bias_cache.keys(): + seqlens = [] + for b, x in zip(batch_sizes, x_list): + for _ in range(b): + seqlens.append(x.shape[1]) + attn_bias = fmha.BlockDiagonalMask.from_seqlens(seqlens) + attn_bias._batch_sizes = batch_sizes + attn_bias_cache[all_shapes] = attn_bias + + if branges is not None: + cat_tensors = index_select_cat([x.flatten(1) for x in x_list], branges).view(1, -1, x_list[0].shape[-1]) + else: + tensors_bs1 = tuple(x.reshape([1, -1, *x.shape[2:]]) for x in x_list) + cat_tensors = torch.cat(tensors_bs1, dim=1) + + return attn_bias_cache[all_shapes], cat_tensors + + +def drop_add_residual_stochastic_depth_list( + x_list: List[Tensor], + residual_func: Callable[[Tensor, Any], Tensor], + sample_drop_ratio: float = 0.0, + scaling_vector=None, +) -> Tensor: + # 1) generate random set of indices for dropping samples in the batch + branges_scales = [get_branges_scales(x, sample_drop_ratio=sample_drop_ratio) for x in x_list] + branges = [s[0] for s in branges_scales] + residual_scale_factors = [s[1] for s in branges_scales] + + # 2) get attention bias and index+concat the tensors + attn_bias, x_cat = get_attn_bias_and_cat(x_list, branges) + + # 3) apply residual_func to get residual, and split the result + residual_list = attn_bias.split(residual_func(x_cat, attn_bias=attn_bias)) # type: ignore + + outputs = [] + for x, brange, residual, residual_scale_factor in zip(x_list, branges, residual_list, residual_scale_factors): + outputs.append(add_residual(x, brange, residual, residual_scale_factor, scaling_vector).view_as(x)) + return outputs + + +class NestedTensorBlock(Block): + def forward_nested(self, x_list: List[Tensor]) -> List[Tensor]: + """ + x_list contains a list of tensors to nest together and run + """ + assert isinstance(self.attn, MemEffAttention) + + if self.training and self.sample_drop_ratio > 0.0: + + def attn_residual_func(x: Tensor, attn_bias=None) -> Tensor: + return self.attn(self.norm1(x), attn_bias=attn_bias) + + def ffn_residual_func(x: Tensor, attn_bias=None) -> Tensor: + return self.mlp(self.norm2(x)) + + x_list = drop_add_residual_stochastic_depth_list( + x_list, + residual_func=attn_residual_func, + sample_drop_ratio=self.sample_drop_ratio, + scaling_vector=self.ls1.gamma if isinstance(self.ls1, LayerScale) else None, + ) + x_list = drop_add_residual_stochastic_depth_list( + x_list, + residual_func=ffn_residual_func, + sample_drop_ratio=self.sample_drop_ratio, + scaling_vector=self.ls2.gamma if isinstance(self.ls1, LayerScale) else None, + ) + return x_list + else: + + def attn_residual_func(x: Tensor, attn_bias=None) -> Tensor: + return self.ls1(self.attn(self.norm1(x), attn_bias=attn_bias)) + + def ffn_residual_func(x: Tensor, attn_bias=None) -> Tensor: + return self.ls2(self.mlp(self.norm2(x))) + + attn_bias, x = get_attn_bias_and_cat(x_list) + x = x + attn_residual_func(x, attn_bias=attn_bias) + x = x + ffn_residual_func(x) + return attn_bias.split(x) + + def forward(self, x_or_x_list): + if isinstance(x_or_x_list, Tensor): + return super().forward(x_or_x_list) + elif isinstance(x_or_x_list, list): + assert XFORMERS_AVAILABLE, "Please install xFormers for nested tensors usage" + return self.forward_nested(x_or_x_list) + else: + raise AssertionError diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/drop_path.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/drop_path.py new file mode 100644 index 0000000000000000000000000000000000000000..10c3bea8e40eec258bbe59087770d230a6375481 --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/drop_path.py @@ -0,0 +1,35 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +# References: +# https://github.com/facebookresearch/dino/blob/master/vision_transformer.py +# https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/drop.py + + +from torch import nn + + +def drop_path(x, drop_prob: float = 0.0, training: bool = False): + if drop_prob == 0.0 or not training: + return x + keep_prob = 1 - drop_prob + shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets + random_tensor = x.new_empty(shape).bernoulli_(keep_prob) + if keep_prob > 0.0: + random_tensor.div_(keep_prob) + output = x * random_tensor + return output + + +class DropPath(nn.Module): + """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).""" + + def __init__(self, drop_prob=None): + super(DropPath, self).__init__() + self.drop_prob = drop_prob + + def forward(self, x): + return drop_path(x, self.drop_prob, self.training) diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/layer_scale.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/layer_scale.py new file mode 100644 index 0000000000000000000000000000000000000000..76a4d0eedb1dc974a45e06fbe77ff3d909e36e55 --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/layer_scale.py @@ -0,0 +1,28 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +# Modified from: https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py#L103-L110 + +from typing import Union + +import torch +from torch import Tensor +from torch import nn + + +class LayerScale(nn.Module): + def __init__( + self, + dim: int, + init_values: Union[float, Tensor] = 1e-5, + inplace: bool = False, + ) -> None: + super().__init__() + self.inplace = inplace + self.gamma = nn.Parameter(init_values * torch.ones(dim)) + + def forward(self, x: Tensor) -> Tensor: + return x.mul_(self.gamma) if self.inplace else x * self.gamma diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/mlp.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/mlp.py new file mode 100644 index 0000000000000000000000000000000000000000..504987b635c9cd582a352fb2381228c9e6cd043c --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/mlp.py @@ -0,0 +1,41 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +# References: +# https://github.com/facebookresearch/dino/blob/master/vision_transformer.py +# https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/mlp.py + + +from typing import Callable, Optional + +from torch import Tensor, nn + + +class Mlp(nn.Module): + def __init__( + self, + in_features: int, + hidden_features: Optional[int] = None, + out_features: Optional[int] = None, + act_layer: Callable[..., nn.Module] = nn.GELU, + drop: float = 0.0, + bias: bool = True, + ) -> None: + super().__init__() + out_features = out_features or in_features + hidden_features = hidden_features or in_features + self.fc1 = nn.Linear(in_features, hidden_features, bias=bias) + self.act = act_layer() + self.fc2 = nn.Linear(hidden_features, out_features, bias=bias) + self.drop = nn.Dropout(drop) + + def forward(self, x: Tensor) -> Tensor: + x = self.fc1(x) + x = self.act(x) + x = self.drop(x) + x = self.fc2(x) + x = self.drop(x) + return x diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/patch_embed.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/patch_embed.py new file mode 100644 index 0000000000000000000000000000000000000000..f880c042ee6a33ef520c6a8c8a686c1d065b8f49 --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/patch_embed.py @@ -0,0 +1,89 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +# References: +# https://github.com/facebookresearch/dino/blob/master/vision_transformer.py +# https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/patch_embed.py + +from typing import Callable, Optional, Tuple, Union + +from torch import Tensor +import torch.nn as nn + + +def make_2tuple(x): + if isinstance(x, tuple): + assert len(x) == 2 + return x + + assert isinstance(x, int) + return (x, x) + + +class PatchEmbed(nn.Module): + """ + 2D image to patch embedding: (B,C,H,W) -> (B,N,D) + + Args: + img_size: Image size. + patch_size: Patch token size. + in_chans: Number of input image channels. + embed_dim: Number of linear projection output channels. + norm_layer: Normalization layer. + """ + + def __init__( + self, + img_size: Union[int, Tuple[int, int]] = 224, + patch_size: Union[int, Tuple[int, int]] = 16, + in_chans: int = 3, + embed_dim: int = 768, + norm_layer: Optional[Callable] = None, + flatten_embedding: bool = True, + ) -> None: + super().__init__() + + image_HW = make_2tuple(img_size) + patch_HW = make_2tuple(patch_size) + patch_grid_size = ( + image_HW[0] // patch_HW[0], + image_HW[1] // patch_HW[1], + ) + + self.img_size = image_HW + self.patch_size = patch_HW + self.patches_resolution = patch_grid_size + self.num_patches = patch_grid_size[0] * patch_grid_size[1] + + self.in_chans = in_chans + self.embed_dim = embed_dim + + self.flatten_embedding = flatten_embedding + + self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_HW, stride=patch_HW) + self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity() + + def forward(self, x: Tensor) -> Tensor: + _, _, H, W = x.shape + patch_H, patch_W = self.patch_size + + assert H % patch_H == 0, f"Input image height {H} is not a multiple of patch height {patch_H}" + assert W % patch_W == 0, f"Input image width {W} is not a multiple of patch width: {patch_W}" + + x = self.proj(x) # B C H W + H, W = x.size(2), x.size(3) + x = x.flatten(2).transpose(1, 2) # B HW C + x = self.norm(x) + if not self.flatten_embedding: + x = x.reshape(-1, H, W, self.embed_dim) # B H W C + return x + + def flops(self) -> float: + Ho, Wo = self.patches_resolution + flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1]) + if self.norm is not None: + flops += Ho * Wo * self.embed_dim + return flops diff --git a/Depth-Anything-V2/depth_anything_v2/dinov2_layers/swiglu_ffn.py b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/swiglu_ffn.py new file mode 100644 index 0000000000000000000000000000000000000000..155a3dd9f6f1a7d0f7bdf9c8f1981e58acb3b19c --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dinov2_layers/swiglu_ffn.py @@ -0,0 +1,63 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. + +from typing import Callable, Optional + +from torch import Tensor, nn +import torch.nn.functional as F + + +class SwiGLUFFN(nn.Module): + def __init__( + self, + in_features: int, + hidden_features: Optional[int] = None, + out_features: Optional[int] = None, + act_layer: Callable[..., nn.Module] = None, + drop: float = 0.0, + bias: bool = True, + ) -> None: + super().__init__() + out_features = out_features or in_features + hidden_features = hidden_features or in_features + self.w12 = nn.Linear(in_features, 2 * hidden_features, bias=bias) + self.w3 = nn.Linear(hidden_features, out_features, bias=bias) + + def forward(self, x: Tensor) -> Tensor: + x12 = self.w12(x) + x1, x2 = x12.chunk(2, dim=-1) + hidden = F.silu(x1) * x2 + return self.w3(hidden) + + +try: + from xformers.ops import SwiGLU + + XFORMERS_AVAILABLE = True +except ImportError: + SwiGLU = SwiGLUFFN + XFORMERS_AVAILABLE = False + + +class SwiGLUFFNFused(SwiGLU): + def __init__( + self, + in_features: int, + hidden_features: Optional[int] = None, + out_features: Optional[int] = None, + act_layer: Callable[..., nn.Module] = None, + drop: float = 0.0, + bias: bool = True, + ) -> None: + out_features = out_features or in_features + hidden_features = hidden_features or in_features + hidden_features = (int(hidden_features * 2 / 3) + 7) // 8 * 8 + super().__init__( + in_features=in_features, + hidden_features=hidden_features, + out_features=out_features, + bias=bias, + ) diff --git a/Depth-Anything-V2/depth_anything_v2/dpt.py b/Depth-Anything-V2/depth_anything_v2/dpt.py new file mode 100644 index 0000000000000000000000000000000000000000..acef20bfcf80318709dcf6c5e8c19b117394a06b --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/dpt.py @@ -0,0 +1,221 @@ +import cv2 +import torch +import torch.nn as nn +import torch.nn.functional as F +from torchvision.transforms import Compose + +from .dinov2 import DINOv2 +from .util.blocks import FeatureFusionBlock, _make_scratch +from .util.transform import Resize, NormalizeImage, PrepareForNet + + +def _make_fusion_block(features, use_bn, size=None): + return FeatureFusionBlock( + features, + nn.ReLU(False), + deconv=False, + bn=use_bn, + expand=False, + align_corners=True, + size=size, + ) + + +class ConvBlock(nn.Module): + def __init__(self, in_feature, out_feature): + super().__init__() + + self.conv_block = nn.Sequential( + nn.Conv2d(in_feature, out_feature, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(out_feature), + nn.ReLU(True) + ) + + def forward(self, x): + return self.conv_block(x) + + +class DPTHead(nn.Module): + def __init__( + self, + in_channels, + features=256, + use_bn=False, + out_channels=[256, 512, 1024, 1024], + use_clstoken=False + ): + super(DPTHead, self).__init__() + + self.use_clstoken = use_clstoken + + self.projects = nn.ModuleList([ + nn.Conv2d( + in_channels=in_channels, + out_channels=out_channel, + kernel_size=1, + stride=1, + padding=0, + ) for out_channel in out_channels + ]) + + self.resize_layers = nn.ModuleList([ + nn.ConvTranspose2d( + in_channels=out_channels[0], + out_channels=out_channels[0], + kernel_size=4, + stride=4, + padding=0), + nn.ConvTranspose2d( + in_channels=out_channels[1], + out_channels=out_channels[1], + kernel_size=2, + stride=2, + padding=0), + nn.Identity(), + nn.Conv2d( + in_channels=out_channels[3], + out_channels=out_channels[3], + kernel_size=3, + stride=2, + padding=1) + ]) + + if use_clstoken: + self.readout_projects = nn.ModuleList() + for _ in range(len(self.projects)): + self.readout_projects.append( + nn.Sequential( + nn.Linear(2 * in_channels, in_channels), + nn.GELU())) + + self.scratch = _make_scratch( + out_channels, + features, + groups=1, + expand=False, + ) + + self.scratch.stem_transpose = None + + self.scratch.refinenet1 = _make_fusion_block(features, use_bn) + self.scratch.refinenet2 = _make_fusion_block(features, use_bn) + self.scratch.refinenet3 = _make_fusion_block(features, use_bn) + self.scratch.refinenet4 = _make_fusion_block(features, use_bn) + + head_features_1 = features + head_features_2 = 32 + + self.scratch.output_conv1 = nn.Conv2d(head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1) + self.scratch.output_conv2 = nn.Sequential( + nn.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1), + nn.ReLU(True), + nn.Conv2d(head_features_2, 1, kernel_size=1, stride=1, padding=0), + nn.ReLU(True), + nn.Identity(), + ) + + def forward(self, out_features, patch_h, patch_w): + out = [] + for i, x in enumerate(out_features): + if self.use_clstoken: + x, cls_token = x[0], x[1] + readout = cls_token.unsqueeze(1).expand_as(x) + x = self.readout_projects[i](torch.cat((x, readout), -1)) + else: + x = x[0] + + x = x.permute(0, 2, 1).reshape((x.shape[0], x.shape[-1], patch_h, patch_w)) + + x = self.projects[i](x) + x = self.resize_layers[i](x) + + out.append(x) + + layer_1, layer_2, layer_3, layer_4 = out + + layer_1_rn = self.scratch.layer1_rn(layer_1) + layer_2_rn = self.scratch.layer2_rn(layer_2) + layer_3_rn = self.scratch.layer3_rn(layer_3) + layer_4_rn = self.scratch.layer4_rn(layer_4) + + path_4 = self.scratch.refinenet4(layer_4_rn, size=layer_3_rn.shape[2:]) + path_3 = self.scratch.refinenet3(path_4, layer_3_rn, size=layer_2_rn.shape[2:]) + path_2 = self.scratch.refinenet2(path_3, layer_2_rn, size=layer_1_rn.shape[2:]) + path_1 = self.scratch.refinenet1(path_2, layer_1_rn) + + out = self.scratch.output_conv1(path_1) + out = F.interpolate(out, (int(patch_h * 14), int(patch_w * 14)), mode="bilinear", align_corners=True) + out = self.scratch.output_conv2(out) + + return out + + +class DepthAnythingV2(nn.Module): + def __init__( + self, + encoder='vitl', + features=256, + out_channels=[256, 512, 1024, 1024], + use_bn=False, + use_clstoken=False + ): + super(DepthAnythingV2, self).__init__() + + self.intermediate_layer_idx = { + 'vits': [2, 5, 8, 11], + 'vitb': [2, 5, 8, 11], + 'vitl': [4, 11, 17, 23], + 'vitg': [9, 19, 29, 39] + } + + self.encoder = encoder + self.pretrained = DINOv2(model_name=encoder) + + self.depth_head = DPTHead(self.pretrained.embed_dim, features, use_bn, out_channels=out_channels, use_clstoken=use_clstoken) + + def forward(self, x): + patch_h, patch_w = x.shape[-2] // 14, x.shape[-1] // 14 + + features = self.pretrained.get_intermediate_layers(x, self.intermediate_layer_idx[self.encoder], return_class_token=True) + + depth = self.depth_head(features, patch_h, patch_w) + depth = F.relu(depth) + + return depth.squeeze(1) + + @torch.no_grad() + def infer_image(self, raw_image, input_size=518): + image, (h, w) = self.image2tensor(raw_image, input_size) + + depth = self.forward(image) + + depth = F.interpolate(depth[:, None], (h, w), mode="bilinear", align_corners=True)[0, 0] + + return depth.cpu().numpy() + + def image2tensor(self, raw_image, input_size=518): + transform = Compose([ + Resize( + width=input_size, + height=input_size, + resize_target=False, + keep_aspect_ratio=True, + ensure_multiple_of=14, + resize_method='lower_bound', + image_interpolation_method=cv2.INTER_CUBIC, + ), + NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), + PrepareForNet(), + ]) + + h, w = raw_image.shape[:2] + + image = cv2.cvtColor(raw_image, cv2.COLOR_BGR2RGB) / 255.0 + + image = transform({'image': image})['image'] + image = torch.from_numpy(image).unsqueeze(0) + + DEVICE = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu' + image = image.to(DEVICE) + + return image, (h, w) diff --git a/Depth-Anything-V2/depth_anything_v2/util/__pycache__/blocks.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/util/__pycache__/blocks.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e38914f952d63cb74a1e60c87c9b9fe746c03861 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/util/__pycache__/blocks.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/util/__pycache__/transform.cpython-312.pyc b/Depth-Anything-V2/depth_anything_v2/util/__pycache__/transform.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..34f5094db951013991231ea332837d7bea56d9f1 Binary files /dev/null and b/Depth-Anything-V2/depth_anything_v2/util/__pycache__/transform.cpython-312.pyc differ diff --git a/Depth-Anything-V2/depth_anything_v2/util/blocks.py b/Depth-Anything-V2/depth_anything_v2/util/blocks.py new file mode 100644 index 0000000000000000000000000000000000000000..9fb66c03702d653f411c59ab9966916c348c7c6e --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/util/blocks.py @@ -0,0 +1,148 @@ +import torch.nn as nn + + +def _make_scratch(in_shape, out_shape, groups=1, expand=False): + scratch = nn.Module() + + out_shape1 = out_shape + out_shape2 = out_shape + out_shape3 = out_shape + if len(in_shape) >= 4: + out_shape4 = out_shape + + if expand: + out_shape1 = out_shape + out_shape2 = out_shape * 2 + out_shape3 = out_shape * 4 + if len(in_shape) >= 4: + out_shape4 = out_shape * 8 + + scratch.layer1_rn = nn.Conv2d(in_shape[0], out_shape1, kernel_size=3, stride=1, padding=1, bias=False, groups=groups) + scratch.layer2_rn = nn.Conv2d(in_shape[1], out_shape2, kernel_size=3, stride=1, padding=1, bias=False, groups=groups) + scratch.layer3_rn = nn.Conv2d(in_shape[2], out_shape3, kernel_size=3, stride=1, padding=1, bias=False, groups=groups) + if len(in_shape) >= 4: + scratch.layer4_rn = nn.Conv2d(in_shape[3], out_shape4, kernel_size=3, stride=1, padding=1, bias=False, groups=groups) + + return scratch + + +class ResidualConvUnit(nn.Module): + """Residual convolution module. + """ + + def __init__(self, features, activation, bn): + """Init. + + Args: + features (int): number of features + """ + super().__init__() + + self.bn = bn + + self.groups=1 + + self.conv1 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups) + + self.conv2 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups) + + if self.bn == True: + self.bn1 = nn.BatchNorm2d(features) + self.bn2 = nn.BatchNorm2d(features) + + self.activation = activation + + self.skip_add = nn.quantized.FloatFunctional() + + def forward(self, x): + """Forward pass. + + Args: + x (tensor): input + + Returns: + tensor: output + """ + + out = self.activation(x) + out = self.conv1(out) + if self.bn == True: + out = self.bn1(out) + + out = self.activation(out) + out = self.conv2(out) + if self.bn == True: + out = self.bn2(out) + + if self.groups > 1: + out = self.conv_merge(out) + + return self.skip_add.add(out, x) + + +class FeatureFusionBlock(nn.Module): + """Feature fusion block. + """ + + def __init__( + self, + features, + activation, + deconv=False, + bn=False, + expand=False, + align_corners=True, + size=None + ): + """Init. + + Args: + features (int): number of features + """ + super(FeatureFusionBlock, self).__init__() + + self.deconv = deconv + self.align_corners = align_corners + + self.groups=1 + + self.expand = expand + out_features = features + if self.expand == True: + out_features = features // 2 + + self.out_conv = nn.Conv2d(features, out_features, kernel_size=1, stride=1, padding=0, bias=True, groups=1) + + self.resConfUnit1 = ResidualConvUnit(features, activation, bn) + self.resConfUnit2 = ResidualConvUnit(features, activation, bn) + + self.skip_add = nn.quantized.FloatFunctional() + + self.size=size + + def forward(self, *xs, size=None): + """Forward pass. + + Returns: + tensor: output + """ + output = xs[0] + + if len(xs) == 2: + res = self.resConfUnit1(xs[1]) + output = self.skip_add.add(output, res) + + output = self.resConfUnit2(output) + + if (size is None) and (self.size is None): + modifier = {"scale_factor": 2} + elif size is None: + modifier = {"size": self.size} + else: + modifier = {"size": size} + + output = nn.functional.interpolate(output, **modifier, mode="bilinear", align_corners=self.align_corners) + + output = self.out_conv(output) + + return output diff --git a/Depth-Anything-V2/depth_anything_v2/util/transform.py b/Depth-Anything-V2/depth_anything_v2/util/transform.py new file mode 100644 index 0000000000000000000000000000000000000000..1cce234c86177e1ad5c84c81c7c1afb16877c9da --- /dev/null +++ b/Depth-Anything-V2/depth_anything_v2/util/transform.py @@ -0,0 +1,158 @@ +import numpy as np +import cv2 + + +class Resize(object): + """Resize sample to given size (width, height). + """ + + def __init__( + self, + width, + height, + resize_target=True, + keep_aspect_ratio=False, + ensure_multiple_of=1, + resize_method="lower_bound", + image_interpolation_method=cv2.INTER_AREA, + ): + """Init. + + Args: + width (int): desired output width + height (int): desired output height + resize_target (bool, optional): + True: Resize the full sample (image, mask, target). + False: Resize image only. + Defaults to True. + keep_aspect_ratio (bool, optional): + True: Keep the aspect ratio of the input sample. + Output sample might not have the given width and height, and + resize behaviour depends on the parameter 'resize_method'. + Defaults to False. + ensure_multiple_of (int, optional): + Output width and height is constrained to be multiple of this parameter. + Defaults to 1. + resize_method (str, optional): + "lower_bound": Output will be at least as large as the given size. + "upper_bound": Output will be at max as large as the given size. (Output size might be smaller than given size.) + "minimal": Scale as least as possible. (Output size might be smaller than given size.) + Defaults to "lower_bound". + """ + self.__width = width + self.__height = height + + self.__resize_target = resize_target + self.__keep_aspect_ratio = keep_aspect_ratio + self.__multiple_of = ensure_multiple_of + self.__resize_method = resize_method + self.__image_interpolation_method = image_interpolation_method + + def constrain_to_multiple_of(self, x, min_val=0, max_val=None): + y = (np.round(x / self.__multiple_of) * self.__multiple_of).astype(int) + + if max_val is not None and y > max_val: + y = (np.floor(x / self.__multiple_of) * self.__multiple_of).astype(int) + + if y < min_val: + y = (np.ceil(x / self.__multiple_of) * self.__multiple_of).astype(int) + + return y + + def get_size(self, width, height): + # determine new height and width + scale_height = self.__height / height + scale_width = self.__width / width + + if self.__keep_aspect_ratio: + if self.__resize_method == "lower_bound": + # scale such that output size is lower bound + if scale_width > scale_height: + # fit width + scale_height = scale_width + else: + # fit height + scale_width = scale_height + elif self.__resize_method == "upper_bound": + # scale such that output size is upper bound + if scale_width < scale_height: + # fit width + scale_height = scale_width + else: + # fit height + scale_width = scale_height + elif self.__resize_method == "minimal": + # scale as least as possbile + if abs(1 - scale_width) < abs(1 - scale_height): + # fit width + scale_height = scale_width + else: + # fit height + scale_width = scale_height + else: + raise ValueError(f"resize_method {self.__resize_method} not implemented") + + if self.__resize_method == "lower_bound": + new_height = self.constrain_to_multiple_of(scale_height * height, min_val=self.__height) + new_width = self.constrain_to_multiple_of(scale_width * width, min_val=self.__width) + elif self.__resize_method == "upper_bound": + new_height = self.constrain_to_multiple_of(scale_height * height, max_val=self.__height) + new_width = self.constrain_to_multiple_of(scale_width * width, max_val=self.__width) + elif self.__resize_method == "minimal": + new_height = self.constrain_to_multiple_of(scale_height * height) + new_width = self.constrain_to_multiple_of(scale_width * width) + else: + raise ValueError(f"resize_method {self.__resize_method} not implemented") + + return (new_width, new_height) + + def __call__(self, sample): + width, height = self.get_size(sample["image"].shape[1], sample["image"].shape[0]) + + # resize sample + sample["image"] = cv2.resize(sample["image"], (width, height), interpolation=self.__image_interpolation_method) + + if self.__resize_target: + if "depth" in sample: + sample["depth"] = cv2.resize(sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST) + + if "mask" in sample: + sample["mask"] = cv2.resize(sample["mask"].astype(np.float32), (width, height), interpolation=cv2.INTER_NEAREST) + + return sample + + +class NormalizeImage(object): + """Normlize image by given mean and std. + """ + + def __init__(self, mean, std): + self.__mean = mean + self.__std = std + + def __call__(self, sample): + sample["image"] = (sample["image"] - self.__mean) / self.__std + + return sample + + +class PrepareForNet(object): + """Prepare sample for usage as network input. + """ + + def __init__(self): + pass + + def __call__(self, sample): + image = np.transpose(sample["image"], (2, 0, 1)) + sample["image"] = np.ascontiguousarray(image).astype(np.float32) + + if "depth" in sample: + depth = sample["depth"].astype(np.float32) + sample["depth"] = np.ascontiguousarray(depth) + + if "mask" in sample: + sample["mask"] = sample["mask"].astype(np.float32) + sample["mask"] = np.ascontiguousarray(sample["mask"]) + + return sample \ No newline at end of file diff --git a/Depth-Anything-V2/requirements.txt b/Depth-Anything-V2/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..552a47316fd8a960bb225ec00280fa7f2a285848 --- /dev/null +++ b/Depth-Anything-V2/requirements.txt @@ -0,0 +1,7 @@ +gradio_imageslider +gradio==4.36.0 +torch +torchvision +opencv-python +matplotlib +huggingface_hub \ No newline at end of file