2020-12-29 18:56:14

docs/tf2/043.md

@@ -146,7 +146,7 @@ data_augmentation = tf.keras.Sequential([
 ]) 
 ```
 
-<aside class="note">**Note:** These layers are active only during training, when you call `model.fit`. They are inactive when the model is used in inference mode in `model.evaulate` or `model.fit`.</aside>
+**Note:** These layers are active only during training, when you call `model.fit`. They are inactive when the model is used in inference mode in `model.evaulate` or `model.fit`.
 
 Let's repeatedly apply these layers to the same image and see the result.
 
@@ -171,13 +171,13 @@ In a moment, you will download `tf.keras.applications.MobileNetV2` for use as yo
 preprocess_input = tf.keras.applications.mobilenet_v2.preprocess_input 
 ```
 
-<aside class="note">**Note:** Alternatively, you could rescale pixel values from `[0,255]` to `[-1, 1]` using a [Rescaling](https://tensorflow.google.cn/api_docs/python/tf/keras/layers/experimental/preprocessing/Rescaling) layer.</aside>
+**Note:** Alternatively, you could rescale pixel values from `[0,255]` to `[-1, 1]` using a [Rescaling](https://tensorflow.google.cn/api_docs/python/tf/keras/layers/experimental/preprocessing/Rescaling) layer.
 
 ```
 rescale = tf.keras.layers.experimental.preprocessing.Rescaling(1./127.5, offset= -1) 
 ```
 
-<aside class="note">**Note:** If using other `tf.keras.applications`, be sure to check the API doc to determine if they expect pixels in `[-1,1]` or `[0,1]`, or use the included `preprocess_input` function.</aside>
+**Note:** If using other `tf.keras.applications`, be sure to check the API doc to determine if they expect pixels in `[-1,1]` or `[0,1]`, or use the included `preprocess_input` function.
 
 ## Create the base model from the pre-trained convnets
 
@@ -755,7 +755,7 @@ plt.show()
 
 ![png](img/cd8127c26455c518a827f0ce6a07b1e0.png)
 
-<aside class="note">**Note:** If you are wondering why the validation metrics are clearly better than the training metrics, the main factor is because layers like `tf.keras.layers.BatchNormalization` and `tf.keras.layers.Dropout` affect accuracy during training. They are turned off when calculating validation loss.</aside>
+**Note:** If you are wondering why the validation metrics are clearly better than the training metrics, the main factor is because layers like `tf.keras.layers.BatchNormalization` and `tf.keras.layers.Dropout` affect accuracy during training. They are turned off when calculating validation loss.
 
 To a lesser extent, it is also because training metrics report the average for an epoch, while validation metrics are evaluated after the epoch, so validation metrics see a model that has trained slightly longer.
 
@@ -765,7 +765,7 @@ In the feature extraction experiment, you were only training a few layers on top
 
 One way to increase performance even further is to train (or "fine-tune") the weights of the top layers of the pre-trained model alongside the training of the classifier you added. The training process will force the weights to be tuned from generic feature maps to features associated specifically with the dataset.
 
-<aside class="note">**Note:** This should only be attempted after you have trained the top-level classifier with the pre-trained model set to non-trainable. If you add a randomly initialized classifier on top of a pre-trained model and attempt to train all layers jointly, the magnitude of the gradient updates will be too large (due to the random weights from the classifier) and your pre-trained model will forget what it has learned.</aside>
+**Note:** This should only be attempted after you have trained the top-level classifier with the pre-trained model set to non-trainable. If you add a randomly initialized classifier on top of a pre-trained model and attempt to train all layers jointly, the magnitude of the gradient updates will be too large (due to the random weights from the classifier) and your pre-trained model will forget what it has learned.
 
 Also, you should try to fine-tune a small number of top layers rather than the whole MobileNet model. In most convolutional networks, the higher up a layer is, the more specialized it is. The first few layers learn very simple and generic features that generalize to almost all types of images. As you go higher up, the features are increasingly more specific to the dataset on which the model was trained. The goal of fine-tuning is to adapt these specialized features to work with the new dataset, rather than overwrite the generic learning.