images with info

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import os
 from PIL import Image
 import torchvision
 from torchvision import transforms
@@ -64,12 +65,12 @@ iface = gr.Interface(
         gr.inputs.Radio(MODELS_TYPE)
     ], 
     outputs=[
-        gr.Text(),
-        gr.Image(),
-        gr.Image()
+        gr.Text(label='Model info'),
+        gr.Image(label='Super Resolution'),
+        gr.Image(label='DTM')
     ],
     examples=[
-        ["demo_imgs/fake.jpg", MODELS_TYPE[0]] # use real image
+        [f"demo_imgs/{name}", MODELS_TYPE[0]] for name in os.listdir('demo_imgs')
     ],
     title="Super Resolution and DTM Estimation",
 description=f"This demo predict Super Resolution and (Super Resolution) DTM from a Grayscale image (if RGB we convert it, for demo reason input is scale to {scale_size}x{scale_size})."

copy_and_transform_imgs.py

@@ -0,0 +1,14 @@
+from osgeo import gdal
+import os
+from PIL import Image
+import numpy as np
+
+path = '/home/super/datasets-nas/hirise_oxia_planum_test_tiles_thruth/'
+
+for i, file_name in enumerate(os.listdir(path)[16:30]):
+    file_path = os.path.join(path, file_name)
+    x = gdal.Open(file_path)
+    x_array = x.ReadAsArray()
+    # print(x_array.shape)
+    pil_img = Image.fromarray(np.uint8(x_array), 'L')
+    pil_img.save(f'demo_imgs/{i}.png')