first commit

Cat_Breed_Classifier_12_class_90_acc.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7419cbb0437f1d8a8fe25ea511c2e881e7c08a279f3d03fe39c7fdc0767215
+size 31323721

app.py

@@ -0,0 +1,57 @@
+import torch
+import torchvision
+from timeit import default_timer as timer
+import gradio as gr
+from typing import Tuple ,Dict
+from model import create_effnetb2_model
+import os
+
+
+
+with open("classes.txt") as f:
+  classes= [line.rstrip() for line in f]
+
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=len(classes))
+
+effnetb2.load_state_dict(
+    torch.load(
+        f="Cat_Breed_Classifier_12_class_90_acc.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+
+def predict(img):
+    start_time = timer()
+    img = effnetb2_transforms(img).unsqueeze(0)
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+    pred_labels_and_probs = {
+        classes[i]: float(pred_probs[0][i]) for i in range(len(classes))
+        }
+    pred_time = round(timer() - start_time, 5)
+    return pred_labels_and_probs, pred_time
+
+title = "Cat Breed Classifier Demo 😼"
+description = "<p style='text-align: center'>Gradio Demo for  Classifying Cat Breeds of these <a href='https://huggingface.co/'>5 different types.<a></p>"
+article = "</br><p style='text-align: center'><a href='https://github.com/Mr-Hexi' target='_blank'>GitHub</a></br>![visitors](https://visitor-badge.glitch.me/badge?page_id=Hexii.Cat-Breed-Classifier)</p> "
+
+
+
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+app = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Label(num_top_classes=5, label="Predictions"),
+        gr.Number(label="Prediction time (s)"),
+    ],
+    examples=example_list,
+    title=title,
+    description=description,
+    article=article,
+    )
+
+app.launch()

classes.txt

@@ -0,0 +1,12 @@
+Abyssinian
+Bengal
+Birman
+Bombay
+British Shorthair
+Egyptian Mau
+Maine Coon
+Persian
+Ragdoll
+Russian Blue
+Siamese
+Sphynx

model.py

@@ -0,0 +1,20 @@
+import torch
+from torch import nn
+import torchvision 
+
+def create_effnetb2_model(num_classes:int=3, 
+                          seed:int=42):
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.efficientnet_b2(weights=weights)
+    
+    for param in model.parameters():
+        param.requires_grad = False
+        
+    torch.manual_seed(seed)
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=num_classes),
+    )
+    
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4