test app

app.py

@@ -1,71 +1,46 @@
-# import streamlit as st
-# import torch
-# import torchvision.transforms as T
-# from PIL import Image
-#
-# # Assuming the necessary packages (featup, clip, etc.) are installed and accessible
-# from featup.util import norm, unnorm
-# from featup.plotting import plot_feats
-#
-# # Setup - ensure the repository content is accessible in the environment
-#
-# # Streamlit UI
-# st.title("Feature Upsampling Demo")
-#
-# # File uploader
-# uploaded_file = st.file_uploader("Choose an image...", type=["png", "jpg", "jpeg"])
-# if uploaded_file is not None:
-#     image = Image.open(uploaded_file).convert("RGB")
-#
-#     # Image preprocessing
-#     input_size = 224
-#     transform = T.Compose([
-#         T.Resize(input_size),
-#         T.CenterCrop((input_size, input_size)),
-#         T.ToTensor(),
-#         norm
-#     ])
-#
-#     image_tensor = transform(image).unsqueeze(0) # Assuming CUDA is available, .cuda()
-#
-#     # Model selection
-#     model_option = st.selectbox(
-#         'Choose a model for feature upsampling',
-#         ('dino16', 'dinov2', 'clip', 'resnet50')
-#     )
-#
-#     if st.button('Upsample Features'):
-#         # Load the selected model
-#         upsampler = torch.hub.load("mhamilton723/FeatUp", model_option).cuda()
-#         hr_feats = upsampler(image_tensor)
-#         lr_feats = upsampler.model(image_tensor)
-#
-#         # Plotting - adjust the plot_feats function or find an alternative to display images in Streamlit
-#         # This step will likely need customization to display within Streamlit's interface
-#         plot_feats(unnorm(image_tensor)[0], lr_feats[0], hr_feats[0])
-
-
 import streamlit as st
 import torch
+import torchvision.transforms as T
+from PIL import Image
+
+# Assuming the necessary packages (featup, clip, etc.) are installed and accessible
+from featup.util import norm, unnorm
+from featup.plotting import plot_feats
+
+# Setup - ensure the repository content is accessible in the environment
+
+# Streamlit UI
+st.title("Feature Upsampling Demo")
+
+# File uploader
+uploaded_file = st.file_uploader("Choose an image...", type=["png", "jpg", "jpeg"])
+if uploaded_file is not None:
+    image = Image.open(uploaded_file).convert("RGB")
+
+    # Image preprocessing
+    input_size = 224
+    transform = T.Compose([
+        T.Resize(input_size),
+        T.CenterCrop((input_size, input_size)),
+        T.ToTensor(),
+        norm
+    ])
 
-def check_gpu_status():
-    # Check if CUDA (GPU support) is available in PyTorch
-    cuda_available = torch.cuda.is_available()
-    gpu_count = torch.cuda.device_count()
-    gpu_name = torch.cuda.get_device_name(0) if cuda_available else "Not Available"
+    image_tensor = transform(image).unsqueeze(0) # Assuming CUDA is available, .cuda()
 
-    return cuda_available, gpu_count, gpu_name
+    # Model selection
+    model_option = st.selectbox(
+        'Choose a model for feature upsampling',
+        ('dino16', 'dinov2', 'clip', 'resnet50')
+    )
 
-# Streamlit page configuration
-st.title("PyTorch GPU Availability Test")
+    if st.button('Upsample Features'):
+        # Load the selected model
+        upsampler = torch.hub.load("mhamilton723/FeatUp", model_option).cuda()
+        hr_feats = upsampler(image_tensor)
+        lr_feats = upsampler.model(image_tensor)
 
-# Checking the GPU status
-cuda_available, gpu_count, gpu_name = check_gpu_status()
+        # Plotting - adjust the plot_feats function or find an alternative to display images in Streamlit
+        # This step will likely need customization to display within Streamlit's interface
+        plot_feats(unnorm(image_tensor)[0], lr_feats[0], hr_feats[0])
 
-# Displaying the results
-if cuda_available:
-    st.success(f"GPU is available! 🎉")
-    st.info(f"Number of GPUs available: {gpu_count}")
-    st.info(f"GPU Name: {gpu_name}")
-else:
-    st.error("GPU is not available. 😢")

requirements.txt

@@ -0,0 +1 @@
+git+https://github.com/mhamilton723/FeatUp