fixes

README.md

@@ -1,14 +1,14 @@
 ---
 title: Depth Image to Autostereogram (Magic Eye)
-emoji: 👀 😵‍💫 👀 
+emoji: 👀 😵‍💫 👀
 colorFrom: green
 colorTo: black
 sdk: gradio
-sdk_version: 3.41.2
+sdk_version: 3.43.2
 app_file: app.py
 pinned: false
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
 
-Depth Image to Autostereogram (Magic Eye)
+Depth Image to Autostereogram (Magic Eye)

app.py

@@ -1,6 +1,6 @@
 from doctest import Example
 import gradio as gr
-from transformers import DPTFeatureExtractor, DPTForDepthEstimation
+from transformers import DPTImageProcessor, DPTForDepthEstimation
 import torch
 import numpy as np
 from PIL import Image, ImageOps
@@ -9,12 +9,14 @@ import glob
 from autostereogram.converter import StereogramConverter
 from datetime import datetime
 import time
+import tempfile
 
-feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-large")
+feature_extractor = DPTImageProcessor.from_pretrained("Intel/dpt-large")
 model = DPTForDepthEstimation.from_pretrained("Intel/dpt-large")
 
 stereo_converter = StereogramConverter()
 
+
 def process_image(image_path):
     print("\n\n\n")
     print("Processing image:", image_path)
@@ -23,7 +25,8 @@ def process_image(image_path):
 
     image = image_raw.resize(
         (1280, int(1280 * image_raw.size[1] / image_raw.size[0])),
-        Image.Resampling.LANCZOS)
+        Image.Resampling.LANCZOS,
+    )
 
     # prepare image for the model
     encoding = feature_extractor(image, return_tensors="pt")
@@ -41,85 +44,59 @@ def process_image(image_path):
         align_corners=False,
     ).squeeze()
     output = prediction.cpu().numpy()
-    depth_image = (output * 255 / np.max(output)).astype('uint8')
-    depth_image_padded = np.array(ImageOps.pad(
-        Image.fromarray(depth_image), (1280, 720)))
+    depth_image = (output * 255 / np.max(output)).astype("uint8")
+    depth_image_padded = np.array(
+        ImageOps.pad(Image.fromarray(depth_image), (1280, 720))
+    )
 
     stereo_image = stereo_converter.convert_depth_to_stereogram_with_thread_pool(
-        depth_image_padded, False).astype(np.uint8)
-
-    stereo_image_pil = Image.fromarray(stereo_image).convert('RGB')
-    image_name = f'stereo_image_{datetime.now().strftime("%Y%m%d_%H%M%S")}.jpg'
-    stereo_image_pil.save(image_name)
-    print(time.time() - last_time)
-    print("\n\n\n")
-    return [depth_image_padded, stereo_image, image_name]
-
+        depth_image_padded, False
+    ).astype(np.uint8)
 
-examples_images = [[f] for f in sorted(glob.glob('examples/*.jpg'))]
+    stereo_image_pil = Image.fromarray(stereo_image).convert("RGB")
+    with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as f:
+        image_name = f.name
+        stereo_image_pil.save(image_name)
 
-blocks = gr.Blocks()
-
-input_image = gr.Image(type="filepath", label="Input Image")
-predicted_depth = gr.Image(label="Predicted Depth", type="pil")
-autostereogram = gr.Image(label="Autostereogram", type="pil")
-file_download = gr.File(label="Download Image")
+    return [depth_image_padded, stereo_image, image_name]
 
 
-def load_example(example_id):
-    processed_examples = [
-        component.preprocess_example(sample)
-        for component, sample in zip(
-            [input_image], examples_images[example_id]
-        )
-    ]
-    if len(processed_examples) == 1:
-        return processed_examples[0]
-    else:
-        return processed_examples
+examples_images = [[f] for f in sorted(glob.glob("examples/*.jpg"))]
 
 
-with blocks:
-    gr.Markdown('''
+with gr.Blocks() as blocks:
+    gr.Markdown(
+        """
 ## Depth Image to Autostereogram (Magic Eye)
 This demo is a variation from the original [DPT Demo](https://huggingface.co/spaces/nielsr/dpt-depth-estimation).
 Zero-shot depth estimation from an image, then it uses [pystereogram](https://github.com/yxiao1996/pystereogram)
 to generate the autostereogram (Magic Eye)
 <base target="_blank">
 
-''')
-
-    with gr.Row():
-        examples_c = gr.components.Dataset(
-            components=[input_image],
-            samples=examples_images,
-            type="index",
-        )
-
-        examples_c.click(
-            load_example,
-            inputs=[examples_c],
-            outputs=[input_image],
-            postprocess=False,
-            queue=False,
-)
-
+"""
+    )
     with gr.Row():
         with gr.Column():
-            input_image.render()
+            input_image = gr.Image(type="filepath", label="Input Image")
             button = gr.Button("Predict")
-            button.click(fn=process_image, inputs=[input_image],
-                         outputs=[predicted_depth,
-                                  autostereogram, file_download],
-                         )
-
         with gr.Column():
-            predicted_depth.render()
+            predicted_depth = gr.Image(label="Predicted Depth", type="pil")
     with gr.Row():
-        autostereogram.render()
+        autostereogram = gr.Image(label="Autostereogram", type="pil")
     with gr.Row():
         with gr.Column():
-            file_download.render()
-
-if __name__ == "__main__":
-    blocks.launch(debug=True)
+            file_download = gr.File(label="Download Image")
+    with gr.Row():
+        gr.Examples(
+            examples=examples_images,
+            fn=process_image,
+            inputs=[input_image],
+            outputs=[predicted_depth, autostereogram, file_download],
+            cache_examples=True,
+        )
+    button.click(
+        fn=process_image,
+        inputs=[input_image],
+        outputs=[predicted_depth, autostereogram, file_download],
+    )
+blocks.launch(debug=True)

requirements.txt

@@ -1,8 +1,7 @@
 torch
-git+https://github.com/nielsrogge/transformers.git@add_dpt_redesign#egg=transformers
-numpy
+transformers
 Pillow
-gradio==3.0b8
+gradio==3.43.2
 jinja2
 transformers
 scikit-image