Added application files

.gitignore

@@ -0,0 +1,2 @@
+__pycache__/
+*.py[cod]

README.md

@@ -1,5 +1,5 @@
 ---
-title: Test-cat Or Dog
+title: Test - Cat or Dog
 emoji: 📊
 colorFrom: blue
 colorTo: red

app.py

@@ -0,0 +1,19 @@
+import torch
+from utils import process_image, load_saved_model
+import gradio as gr
+
+MODEL_PATH = "model.pt"
+CATEGORIES = ("Dog", "Cat")
+model = load_saved_model(MODEL_PATH)
+
+def predict_pet(image):
+    with torch.no_grad():
+        model.eval()
+        x = process_image(image)
+        probs = model(x).squeeze().tolist()
+
+    return dict(zip(CATEGORIES, probs))
+
+demo = gr.Interface(fn=predict_pet, inputs=gr.Image(label="Image"), outputs=gr.Label(label="Type of Pet"), allow_flagging="never",
+                    title="Cat or Dog ?", examples="examples", description="This is a small image classification model for cats and dogs")
+demo.launch()

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e64468ae993ab21d24e47258f71f3333fd73145de5d7e8bfa1908bec33e1215
+size 103037468

utils.py

@@ -0,0 +1,24 @@
+import numpy as np
+import torch
+import torch.nn as nn
+import torchvision.transforms as T
+
+DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+transforms = T.Compose([T.ToPILImage(), T.Resize(size=224), T.ToTensor()])
+
+def load_saved_model(path: str, device:torch.device = DEVICE) -> nn.Module:
+    """
+    Load the PyTorch model
+    """
+    loaded_trace = torch.jit.load(path, map_location=device)
+    model = nn.Sequential(loaded_trace, nn.Softmax(dim=1))
+    return model
+
+def process_image(x: np.ndarray, device:torch.device = DEVICE) -> torch.Tensor:
+    """
+    Takes a numpy array provided by gradio as input and returns a ready to be used tensor with the same processing use for training.
+    """
+    x = transforms(x)
+    x = x.unsqueeze(0)
+    x = x.to(device)
+    return x