Update app.py

app.py

@@ -1,71 +1,66 @@
-import numpy as np
-import math
+import mxnet as mx
 import matplotlib.pyplot as plt
-import onnxruntime as rt
-import cv2
-import json
+import numpy as np
+from collections import namedtuple
+from mxnet.gluon.data.vision import transforms
+import os
 import gradio as gr
-from huggingface_hub import hf_hub_download
-import onnxruntime as rt
 
-modele = hf_hub_download(repo_id="onnx/Inception-1-int8", filename="inception-v1-12-int8.onnx")
-# load the labels text file
-labels = json.load(open("labels_maps.txt", "r"))
+from PIL import Image
+import imageio
+import onnxruntime as ort
 
-# set image file dimensions to 224x224 by resizing and cropping image from center
-def pre_process_edgetpu(img, dims):
-    output_height, output_width, _ = dims
-    img = resize_with_aspectratio(img, output_height, output_width, inter_pol=cv2.INTER_LINEAR)
-    img = center_crop(img, output_height, output_width)
-    img = np.asarray(img, dtype='float32')
-    # converts jpg pixel value from [0 - 255] to float array [-1.0 - 1.0]
-    img -= [127.0, 127.0, 127.0]
-    img /= [128.0, 128.0, 128.0]
+def get_image(path):
+    '''
+        Using path to image, return the RGB load image
+    '''
+    img = imageio.imread(path, pilmode='RGB')
     return img
 
-# resize the image with a proportional scale
-def resize_with_aspectratio(img, out_height, out_width, scale=87.5, inter_pol=cv2.INTER_LINEAR):
-    height, width, _ = img.shape
-    new_height = int(100. * out_height / scale)
-    new_width = int(100. * out_width / scale)
-    if height > width:
-        w = new_width
-        h = int(new_height * height / width)
-    else:
-        h = new_height
-        w = int(new_width * width / height)
-    img = cv2.resize(img, (w, h), interpolation=inter_pol)
-    return img
+# Pre-processing function for ImageNet models using numpy
+def preprocess(img):
+    '''
+    Preprocessing required on the images for inference with mxnet gluon
+    The function takes loaded image and returns processed tensor
+    '''
+    img = np.array(Image.fromarray(img).resize((224, 224))).astype(np.float32)
+    img[:, :, 0] -= 123.68
+    img[:, :, 1] -= 116.779
+    img[:, :, 2] -= 103.939
+    img[:,:,[0,1,2]] = img[:,:,[2,1,0]]
+    img = img.transpose((2, 0, 1))
+    img = np.expand_dims(img, axis=0)
 
-# crop the image around the center based on given height and width
-def center_crop(img, out_height, out_width):
-    height, width, _ = img.shape
-    left = int((width - out_width) / 2)
-    right = int((width + out_width) / 2)
-    top = int((height - out_height) / 2)
-    bottom = int((height + out_height) / 2)
-    img = img[top:bottom, left:right]
     return img
 
+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/onnx/models/raw/main/vision/classification/inception_and_googlenet/googlenet/model/googlenet-9.onnx")
+
+ort_session = ort.InferenceSession("googlenet-9.onnx")
+
+    
+def predict(path):
+    img_batch = preprocess(get_image(path))
+
+    outputs = ort_session.run(
+        None,
+        {"data_0": img_batch.astype(np.float32)},
+    )
 
-sess = rt.InferenceSession('inception-v1-12.onnx')
+    a = np.argsort(-outputs[0].flatten())
+    results = {}
+    for i in a[0:5]:
+        results[labels[i]]=float(outputs[0][0][i])
+    return results
+       
 
-def inference(img):
-  img = cv2.imread(img)
-  img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
-  
-  img = pre_process_edgetpu(img, (224, 224, 3))
-  
-  img_batch = np.expand_dims(img, axis=0)
+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."
 
-  results = sess.run(["Softmax:0"], {"images:0": img_batch})[0]
-  result = reversed(results[0].argsort()[-5:])
-  resultdic = {}
-  for r in result:
-      resultdic[labels[str(r)]] = float(results[0][r])
-  return resultdic
-  
-title="EfficientNet-Lite4"
-description="EfficientNet-Lite 4 is the largest variant and most accurate of the set of EfficientNet-Lite model. It is an integer-only quantized model that produces the highest accuracy of all of the EfficientNet models. It achieves 80.4% ImageNet top-1 accuracy, while still running in real-time (e.g. 30ms/image) on a Pixel 4 CPU."
 examples=[['catonnx.jpg']]
-gr.Interface(inference,gr.inputs.Image(type="filepath"),"label",title=title,description=description,examples=examples).launch()
+gr.Interface(predict,gr.inputs.Image(type='filepath'),"label",title=title,description=description,examples=examples).launch(enable_queue=True,debug=True)