Upload 15 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+examples/4969.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,64 @@
+
+import gradio as gr
+import os
+import torch
+
+from model import create_vit_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+class_names =  ['dew',
+ 'fogsmog',
+ 'frost',
+ 'glaze',
+ 'hail',
+ 'lightning',
+ 'rain',
+ 'rainbow',
+ 'rime',
+ 'sandstorm',
+ 'snow']
+
+vitb16, vitb16_transforms = create_vit_model(num_classes=len(class_names))
+
+vitb16.load_state_dict(
+    torch.load("vitb16_feature_extractor_weather_rcg.pth",
+               map_location=torch.device("cpu")
+               )
+    )
+
+def predict(img):
+
+  start_timer = timer()
+
+  img = vitb16_transforms(img).unsqueeze(0)
+
+  vitb16.eval()
+  with torch.inference_mode():
+    pred_probs = torch.softmax(vitb16(img), dim=1)
+
+  pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+  pred_timer = round(timer()- start_timer, 4)
+
+  return pred_labels_and_probs, pred_timer
+
+
+title = "Wather Recognition"
+
+description = "A ViTb16 Feature Extractor CV model to recognize weather conditions"
+
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Image(type="pil"),
+    outputs=[
+        gr.Label(num_top_classes=11, label="Predictions"),
+        gr.Number(label="Prediction time(s)")],
+    examples=example_list,
+    title=title,
+    description=description
+)
+
+demo.launch()

model.py

@@ -0,0 +1,21 @@
+import torch
+import torchvision
+
+from torch import nn
+
+def create_vit_model(num_classes:int=11, seed: int=42):
+  vitb16_weights = torchvision.models.ViT_B_16_Weights.DEFAULT
+
+  vitb16_transforms = vitb16_weights.transforms()
+
+  model = torchvision.models.vit_b_16(weights=vitb16_weights)
+
+  for param in model.parameters():
+    param.requires_grad = False
+
+  torch.manual_seed(seed)
+  model.heads = nn.Sequential(
+      nn.Linear(in_features=768, out_features=num_classes)
+  )
+
+  return model, vitb16_transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.2.1
+torchvision==0.17.1
+gradio==4.28.3

vitb16_feature_extractor_weather_rcg.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b425ff809b0027fffa43c4bae5071376afc2ced56bc8f30e8a8060b9efba068a
+size 343291310