- Related Questions & Answers
- How can Tensorflow used with the pre-trained model to compile the model?
- How can Tensorflow and pre-trained model be used to continue training the model using Python?
- How can Tensorflow and pre-trained model be used to create base model from pre-trained convnets?
- How can Tensorflow and pre-trained model be used to visualize the data using Python?
- How can Tensorflow and pre-trained model be used to add classification head to the model?
- How can Tensorflow and pre-trained model be used for feature extraction?
- How can Tensorflow and pre-trained model be used for fine tuning?
- How can Tensorflow be used to compile the model using Python?
- How can Tensorflow and pre-trained model be used to understand the learning curve?
- How can Tensorflow and pre-trained model be used to chain data augmentation, rescaling and base model?
- How can Tensorflow be used to compile and fit the model using Python?
- How can Tensorflow be used to compile the exported model using Python?
- How can Tensorflow and pre-trained model be used to configure the dataset for performance?
- How can Tensorflow and pre-trained model after recompiling be used to visualize the data?
- How can Tensorflow be used with pre-trained model to rescale pixel values?

- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who

Tensorflow and the pre-trained model can be used to compile the model by using the ‘compile’ method. Prior to this, the ‘base_learning_rate’ is also defined.

**Read More:**
What is TensorFlow and how Keras work with TensorFlow to create Neural Networks?

A neural network that contains at least one layer is known as a convolutional layer. We can use the Convolutional Neural Network to build learning model.

We will understand how to classify images of cats and dogs with the help of transfer learning from a pre-trained network. The intuition behind transfer learning for image classification is, if a model is trained on a large and general dataset, this model can be used to effectively serve as a generic model for the visual world. It would have learned the feature maps, which means the user won’t have to start from scratch by training a large model on a large dataset.

**Read More:**
How can a customized model be pre-trained?

We are using the Google Colaboratory to run the below code. Google Colab or Colaboratory helps run Python code over the browser and requires zero configuration and free access to GPUs (Graphical Processing Units). Colaboratory has been built on top of Jupyter Notebook.

print("The model is being compiled") base_learning_rate = 0.0001 model.compile(optimizer=tf.keras.optimizers.Adam(lr=base_learning_rate), loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), metrics=['accuracy']) print("The base architecture of the model") model.summary()

Code credit −https://www.tensorflow.org/tutorials/images/transfer_learning

The model is being compiled The base architecture of the model Model: "model" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_3 (InputLayer) [(None, 160, 160, 3)] 0 _________________________________________________________________ sequential_1 (Sequential) (None, 160, 160, 3) 0 _________________________________________________________________ tf.math.truediv (TFOpLambda) (None, 160, 160, 3) 0 _________________________________________________________________ tf.math.subtract (TFOpLambda (None, 160, 160, 3) 0 _________________________________________________________________ mobilenetv2_1.00_160 (Functi (None, 5, 5, 1280) 2257984 _________________________________________________________________ global_average_pooling2d_2 ( (None, 1280) 0 _________________________________________________________________ dropout (Dropout) (None, 1280) 0 _________________________________________________________________ dense_2 (Dense) (None, 1) 1281 ================================================================= Total params: 2,259,265 Trainable params: 1,281 Non-trainable params: 2,257,984

The model is compiled before it is trained.

Since there are two classes, a binary cross-entropy loss is used with from_logits=True since the model provides a linear output.

The 2.5M parameters in MobileNet are frozen, but it contains 1.2K trainable parameters in the Dense layer.

These layers are divided between two tf.Variable objects, the weights and biases.

Advertisements