Update app.py

app.py

@@ -4,10 +4,10 @@ import torchvision.transforms as transforms
 
 device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
 
-resnet50 = torch.hub.load('NVIDIA/DeepLearningExamples:torchhub', 'nvidia_resnet50', pretrained=True)
+resneXt = torch.hub.load('NVIDIA/DeepLearningExamples:torchhub', 'nvidia_resneXt')
 utils = torch.hub.load('NVIDIA/DeepLearningExamples:torchhub', 'nvidia_convnets_processing_utils')
 
-resnet50.eval().to(device)
+resneXt.eval().to(device)
 
 def inference(img):
   img_transforms = transforms.Compose(
@@ -28,16 +28,16 @@ def inference(img):
   ).to(device)
  
   with torch.no_grad():
-    output = torch.nn.functional.softmax(resnet50(batch), dim=1)      
+    output = torch.nn.functional.softmax(resneXt(batch), dim=1)
     
   results = utils.pick_n_best(predictions=output, n=5)
   
   return results
   
-title="ResNet50"
-description="Gradio demo for ResNet50, ResNet50 model trained with mixed precision using Tensor Cores. To use it, simply upload your image or click on one of the examples below. Read more at the links below"
+title="ResNeXt101"
+description="Gradio demo for ResNeXt101, ResNet with bottleneck 3x3 Convolutions substituted by 3x3 Grouped Convolutions, trained with mixed precision using Tensor Cores. To use it, simply upload your image or click on one of the examples below. Read more at the links below"
 
-article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1512.03385'>Deep Residual Learning for Image Recognition</a> | <a href='https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Classification/ConvNets/resnet50v1.5'>Github Repo</a></p>"
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1611.05431'>Aggregated Residual Transformations for Deep Neural Networks</a> | <a href='https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Classification/ConvNets/resnext101-32x4d'>Github Repo</a></p>"
 
 examples=[['food.jpeg']]
 gr.Interface(inference,gr.inputs.Image(type="pil"),"text",title=title,description=description,article=article,examples=examples).launch(enable_queue=True)