upload app

.gitattributes

@@ -33,3 +33,6 @@ 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
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.gradio

README.md

@@ -8,6 +8,7 @@ sdk_version: 5.9.1
 app_file: app.py
 pinned: false
 license: mit
+branch: test
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,24 @@
+import os
+import gradio as gr
+from model import predict
+
+description = """
+- This work is a part of the [DepthPro: Beyond Depth Estimation](https://github.com/geetu040/depthpro-beyond-depth) repository, which further explores this model's capabilities on:
+    - Image Segmentation - Human Segmentation
+    - Image Super Resolution - 384px to 1536px (4x Upscaling)
+    - Image Super Resolution - 256px to 1024px (4x Upscaling)
+"""
+examples_dir = "assets/examples/"
+examples = [[os.path.join(examples_dir, filename)] for filename in os.listdir(examples_dir)]
+
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
+    title="DepthPro: Segmentation Human",
+    description=description,
+    examples=examples,
+)
+
+if __name__ == "__main__":
+    interface.launch()

model.py

@@ -0,0 +1,65 @@
+from PIL import Image
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from huggingface_hub import hf_hub_download
+
+# custom installation from this PR: https://github.com/huggingface/transformers/pull/34583
+# !pip install git+https://github.com/geetu040/transformers.git@depth-pro-projects#egg=transformers
+from transformers import DepthProConfig, DepthProImageProcessorFast, DepthProForDepthEstimation
+
+# initialize model
+config = DepthProConfig(use_fov_model=False)
+model = DepthProForDepthEstimation(config)
+features = config.fusion_hidden_size
+semantic_classifier_dropout = 0.1
+num_labels = 1
+model.head.head = nn.Sequential(
+    nn.Conv2d(features, features, kernel_size=3, padding=1, bias=False),
+    nn.BatchNorm2d(features),
+    nn.ReLU(),
+    nn.Dropout(semantic_classifier_dropout),
+    nn.Conv2d(features, features, kernel_size=1),
+    nn.ConvTranspose2d(features, num_labels, kernel_size=2, stride=2, padding=0, bias=True),
+)
+
+# load weights
+weights_path = hf_hub_download(repo_id="geetu040/DepthPro_Segmentation_Human", filename="model_weights.pth")
+model.load_state_dict(torch.load(weights_path, map_location=torch.device('cpu'), weights_only=True))
+
+# load to device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model = model.to(device)
+
+# load image processor
+image_processor = DepthProImageProcessorFast()
+
+def predict(image):
+	# inference
+
+	image = image.convert("RGB")
+
+	# prepare image for the model
+	inputs = image_processor(images=image, return_tensors="pt")
+	inputs = {k: v.to(device) for k, v in inputs.items()}
+
+	# inference
+	with torch.no_grad():
+		output = model(**inputs)
+
+	# convert tensors to PIL.Image
+	output = output[0]                 # get output logits
+	output = F.interpolate(
+		output.unsqueeze(0),
+		size=(image.height, image.width)
+	)                                  # interpolate to match size
+	output = output.squeeze()          # get first and only batch and channel
+	output = output.sigmoid()          # apply sigmoid for binary segmentation
+	output = (output > 0.5).float()    # threshold to create binary mask
+	output = output.cpu()              # unload from cuda if used
+	output = output * 255              # convert [0, 1] to [0, 255]
+	output = output.numpy()            # convert to numpy
+	output = output.astype('uint8')    # convert to PIL.Image compatible format
+	output = Image.fromarray(output)   # create PIL.Image object
+
+	return output

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+numpy
+pillow
+torch
+torchvision
+git+https://github.com/geetu040/transformers.git@depth-pro-projects#egg=transformers