diff --git a/pytorch_vision_alexnet.md b/pytorch_vision_alexnet.md
index 8a6979e6..bae4c168 100644
--- a/pytorch_vision_alexnet.md
+++ b/pytorch_vision_alexnet.md
@@ -61,9 +61,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_densenet.md b/pytorch_vision_densenet.md
index b33a7ba7..641a0abd 100644
--- a/pytorch_vision_densenet.md
+++ b/pytorch_vision_densenet.md
@@ -65,9 +65,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_ghostnet.md b/pytorch_vision_ghostnet.md
index 33a4accb..233c5c8e 100644
--- a/pytorch_vision_ghostnet.md
+++ b/pytorch_vision_ghostnet.md
@@ -61,9 +61,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_googlenet.md b/pytorch_vision_googlenet.md
index 660c82d8..3136e227 100644
--- a/pytorch_vision_googlenet.md
+++ b/pytorch_vision_googlenet.md
@@ -61,9 +61,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 
 ### Model Description
diff --git a/pytorch_vision_hardnet.md b/pytorch_vision_hardnet.md
index 3a9234f0..34f8663e 100644
--- a/pytorch_vision_hardnet.md
+++ b/pytorch_vision_hardnet.md
@@ -65,9 +65,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_ibnnet.md b/pytorch_vision_ibnnet.md
index 98dcfdf9..3b0e5d40 100644
--- a/pytorch_vision_ibnnet.md
+++ b/pytorch_vision_ibnnet.md
@@ -61,9 +61,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_inception_v3.md b/pytorch_vision_inception_v3.md
index 19a2f556..c79a2aec 100644
--- a/pytorch_vision_inception_v3.md
+++ b/pytorch_vision_inception_v3.md
@@ -61,9 +61,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_meal_v2.md b/pytorch_vision_meal_v2.md
index c3540aaf..6989bf6d 100644
--- a/pytorch_vision_meal_v2.md
+++ b/pytorch_vision_meal_v2.md
@@ -16,6 +16,12 @@ accelerator: cuda
 order: 10
 ---
 
+We require one additional Python dependency
+
+```bash
+!pip install timm
+```
+
 ```python
 import torch
 # list of models: 'mealv1_resnest50', 'mealv2_resnest50', 'mealv2_resnest50_cutmix', 'mealv2_resnest50_380x380', 'mealv2_mobilenetv3_small_075', 'mealv2_mobilenetv3_small_100', 'mealv2_mobilenet_v3_large_100', 'mealv2_efficientnet_b0'
@@ -63,9 +69,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
@@ -86,13 +107,13 @@ In this paper, we introduce a simple yet effective approach that can boost the v
 
 ### References
 
-Please refer to our papers [MEAL V2](https://arxiv.org/pdf/2009.08453.pdf), [MEAL](https://arxiv.org/pdf/1812.02425.pdf) for more details.
-
-    @article{shen2020mealv2,
-        title={MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks},
-        author={Shen, Zhiqiang and Savvides, Marios},
-        journal={arXiv preprint arXiv:2009.08453},
-        year={2020}
+Please refer to our papers [MEAL V2](https://arxiv.org/pdf/2009.08453.pdf), [MEAL](https://arxiv.org/pdf/1812.02425.pdf) for more details.
+
+    @article{shen2020mealv2,
+        title={MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks},
+        author={Shen, Zhiqiang and Savvides, Marios},
+        journal={arXiv preprint arXiv:2009.08453},
+        year={2020}
     }
 
 	@inproceedings{shen2019MEAL,
@@ -100,4 +121,4 @@ Please refer to our papers [MEAL V2](https://arxiv.org/pdf/2009.08453.pdf), [MEA
 		author = {Shen, Zhiqiang and He, Zhankui and Xue, Xiangyang},
 		booktitle = {AAAI},
 		year = {2019}
-	}
\ No newline at end of file
+	}
diff --git a/pytorch_vision_mobilenet_v2.md b/pytorch_vision_mobilenet_v2.md
index a7baa5cf..c81382a4 100644
--- a/pytorch_vision_mobilenet_v2.md
+++ b/pytorch_vision_mobilenet_v2.md
@@ -61,9 +61,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_proxylessnas.md b/pytorch_vision_proxylessnas.md
index 235fa965..9570b18e 100644
--- a/pytorch_vision_proxylessnas.md
+++ b/pytorch_vision_proxylessnas.md
@@ -63,9 +63,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_resnest.md b/pytorch_vision_resnest.md
index c90b344c..9801bb50 100644
--- a/pytorch_vision_resnest.md
+++ b/pytorch_vision_resnest.md
@@ -64,9 +64,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_resnet.md b/pytorch_vision_resnet.md
index f3d1d14a..0ce5a3e4 100644
--- a/pytorch_vision_resnet.md
+++ b/pytorch_vision_resnet.md
@@ -66,9 +66,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_shufflenet_v2.md b/pytorch_vision_shufflenet_v2.md
index 13818f11..572ed1ea 100644
--- a/pytorch_vision_shufflenet_v2.md
+++ b/pytorch_vision_shufflenet_v2.md
@@ -61,9 +61,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_squeezenet.md b/pytorch_vision_squeezenet.md
index f494ee11..423a2295 100644
--- a/pytorch_vision_squeezenet.md
+++ b/pytorch_vision_squeezenet.md
@@ -63,9 +63,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_vgg.md b/pytorch_vision_vgg.md
index 1749cb14..35859875 100644
--- a/pytorch_vision_vgg.md
+++ b/pytorch_vision_vgg.md
@@ -69,9 +69,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description
 
diff --git a/pytorch_vision_wide_resnet.md b/pytorch_vision_wide_resnet.md
index e09ba008..4f734bda 100644
--- a/pytorch_vision_wide_resnet.md
+++ b/pytorch_vision_wide_resnet.md
@@ -64,9 +64,24 @@ with torch.no_grad():
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
-print(torch.nn.functional.softmax(output[0], dim=0))
+probabilities = torch.nn.functional.softmax(output[0], dim=0)
+print(probabilities)
+```
 
 ```
+# Download ImageNet labels
+!wget https://github.com/raw/pytorch/hub/master/imagenet_classes.txt
+```
+
+```
+# Read the categories
+with open("imagenet_classes.txt", "r") as f:
+    categories = [s.strip() for s in f.readlines()]
+# Show top categories per image
+top5_prob, top5_catid = torch.topk(probabilities, 5)
+for i in range(top5_prob.size(0)):
+    print(categories[top5_catid[i]], top5_prob[i].item())
+```
 
 ### Model Description