first-commit

app.py

@@ -0,0 +1,47 @@
+
+import gradio as gr
+from model import model_classification
+
+path = 'efficient_cat_dog.pth'
+class_names = ['cat','dog']
+
+
+model,transforms = model_classification()
+model.load_state_dict(torch.load(path))
+
+
+def predict(img):
+
+    img = transforms(img).unsqueeze(0)
+
+    model.eval()
+
+    with torch.inference_mode():
+        logits = model(img)
+
+    pred_probs = torch.softmax(logits,dim=1)
+
+    pred_label_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+
+    return pred_label_and_probs
+
+
+title = 'Cat and Dog classification'
+description = 'An EfficientNetB0 feature extractor computert vision model to classify the cats and dogs'
+
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+
+demo = gr.Interface(fn=predict,
+                    inputs=gr.Image(type='pil'),
+                    outputs=gr.Label(num_top_classes=2,label='Predictions'),
+                    title=title,
+                    examples=example_list,
+                    description=description,
+
+                             )
+
+
+
+demo.launch(share=True)

efficient_cat_dog.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0779d727b6e18eeb90ea4253776da7e3e4618f8ffc59d4481e128aef27984978
+size 16339558

model.py

@@ -0,0 +1,25 @@
+
+import torch
+from torch import nn
+import torchvision
+from torchvision import models
+
+
+def model_classification():
+
+    weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT
+
+    model = models.efficientnet_b0(weights=weights)
+    tranforms = models.EfficientNet_B0_Weights.DEFAULT.transforms()
+    model.classifier[1] = nn.Linear(1280,2)
+
+    for params in model.parameters():
+        params.requires_grad=False
+
+    
+
+    return model,tranforms
+
+
+
+    

requirements.txt

@@ -0,0 +1,4 @@
+
+torch==2.2.2
+torchvision==0.17.2
+gradio==4.31.5