Update app.py

app.py

@@ -1,50 +1,60 @@
-import mxnet as mx
-import matplotlib.pyplot as plt
+import onnx
 import numpy as np
-from collections import namedtuple
-from mxnet.gluon.data.vision import transforms
+import onnxruntime as ort
+from PIL import Image
+import cv2
 import os
 import gradio as gr
 
-from PIL import Image
-import imageio
-import onnxruntime as ort
+os.system("wget https://s3.amazonaws.com/onnx-model-zoo/synset.txt")
 
-mx.test_utils.download('https://s3.amazonaws.com/model-server/inputs/kitten.jpg')
 
-mx.test_utils.download('https://s3.amazonaws.com/onnx-model-zoo/synset.txt')
 with open('synset.txt', 'r') as f:
     labels = [l.rstrip() for l in f]
     
-os.system("wget https://github.com/AK391/models/raw/main/vision/classification/shufflenet/model/shufflenet-v2-10.onnx")
+os.system("wget https://github.com/onnx/models/raw/main/vision/classification/shufflenet/model/shufflenet-v2-12-int8.onnx")
 
-ort_session = ort.InferenceSession("shufflenet-v2-10.onnx")
+os.system("wget https://s3.amazonaws.com/model-server/inputs/kitten.jpg")
 
+
+
+model_path = 'shufflenet-v2-12-int8.onnx'
+model = onnx.load(model_path)
+session = ort.InferenceSession(model.SerializeToString())
+
+def get_image(path):
+    with Image.open(path) as img:
+        img = np.array(img.convert('RGB'))
+    return img
     
+def preprocess(img):
+    img = img / 255.
+    img = cv2.resize(img, (256, 256))
+    h, w = img.shape[0], img.shape[1]
+    y0 = (h - 224) // 2
+    x0 = (w - 224) // 2
+    img = img[y0 : y0+224, x0 : x0+224, :]
+    img = (img - [0.485, 0.456, 0.406]) / [0.229, 0.224, 0.225]
+    img = np.transpose(img, axes=[2, 0, 1])
+    img = img.astype(np.float32)
+    img = np.expand_dims(img, axis=0)
+    return img
+
 def predict(path):
-    input_image = Image.open(path)
-    preprocess = transforms.Compose([
-        transforms.Resize(256),
-        transforms.CenterCrop(224),
-        transforms.ToTensor(),
-        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
-    input_tensor = preprocess(input_image)
-    input_batch = input_tensor.unsqueeze(0)
-    outputs = ort_session.run(
-        None,
-        {"input": input_batch.astype(np.float32)},
-    )
-
-    a = np.argsort(outputs[0].flatten())
+    img = get_image(path)
+    img = preprocess(img)
+    ort_inputs = {session.get_inputs()[0].name: img}
+    preds = session.run(None, ort_inputs)[0]
+    preds = np.squeeze(preds)
+    a = np.argsort(preds)
     results = {}
-    for i in a[0:5]:
-        results[labels[i]]=float(outputs[0][0][i])
+    for i in a[0:5]:    
+        results[labels[a[i]]] = float(preds[a[i]])
     return results
        
 
-title="GoogleNet"
-description="GoogLeNet is the name of a convolutional neural network for classification, which competed in the ImageNet Large Scale Visual Recognition Challenge in 2014."
+title="ShuffleNet-v2"
+description="ShuffleNet is a deep convolutional network for image classification. ShuffleNetV2 is an improved architecture that is the state-of-the-art in terms of speed and accuracy tradeoff used for image classification."
 
-examples=[['catonnx.jpg']]
+examples=[['kitten.jpg']]
 gr.Interface(predict,gr.inputs.Image(type='filepath'),"label",title=title,description=description,examples=examples).launch(enable_queue=True,debug=True)