commit from ssq

README.md

@@ -1,14 +0,0 @@
----
-title: Histoformer
-emoji: 🦀
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 5.0.1
-app_file: app.py
-pinned: false
-license: mit
-short_description: Adverse Weather Removal
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,10 +1,32 @@
+import torch
 import gradio as gr
-from transformers import pipeline
+import numpy as np
+import torch.nn.functional as F
 
-pipeline = pipeline(task="image-to-image", model="sunsean/Histoformer")
+from Allweather.util import load_img
+from basicsr.models.archs.histoformer_arch import Histoformer
+
+model_restoration = Histoformer()
+checkpoint = torch.load("Allweather/pretrained_models/net_g_real.pth")
+model_restoration.load_state_dict(checkpoint['params'])
+model_restoration.cuda()
+model_restoration = nn.DataParallel(model_restoration)
+
+def preprocess(file_, factor = 8):
+    img = np.float32(load_img(file_))/255.
+    img = torch.from_numpy(img).permute(2,0,1)
+    input_ = img.unsqueeze(0).cuda()
+
+    # Padding in case images are not multiples of 8
+    h,w = input_.shape[2], input_.shape[3]
+    H,W = ((h+factor)//factor)*factor, ((w+factor)//factor)*factor
+    padh = H-h if h%factor!=0 else 0
+    padw = W-w if w%factor!=0 else 0
+    input_ = F.pad(input_, (0,padw,0,padh), 'reflect')
+    return input_
 
 def predict(input_img):
-    prediction = pipeline(input_img)
+    prediction = model_restoration(preprocess(input_img))
     return input_img, prediction 
 
 gradio_app = gr.Interface(

git.bash

@@ -1 +1,3 @@
-git add . && git commit -m 'Add file' && git push
+git add .
+git commit -m "commit from $USER"
+git push

requirements.txt

@@ -1,2 +0,0 @@
-transformers
-torch