Answer / Astha Tulsyan

To retrain an image classifier for new categories using transfer learning, follow these steps:

1. Find a pre-trained model (e.g., Inception V3) on ImageNet dataset with the desired number of output classes.

2. Download the weights of the pre-trained model and extract the feature extractor (without the final fully connected layers).

3. Prepare new labeled data for the target categories, resizing them to match the input size of the feature extractor.

4. Use the feature extractor to get feature vectors from the new data.

5. Fine-tune a small number of fully connected layers on top of the feature extractor using your labeled data.

6. Train the model with the fine-tuned layers and evaluate its performance on validation data.

How does tensorflow use python api?

1 Answers  

---

What are the various dashboards in Tensorflow?

1 Answers  

---

Can you explain data formats in tensorflow?

1 Answers  

---

Can I run tensorboard without tensorflow?

1 Answers  

---

What do you understand by deep speech?

1 Answers  

---

What is autograph ?

1 Answers  

---

What if a file is corrupted or missing in a dataset?

1 Answers  

---

What is the difference between tf.variable and tf.placeholder?

1 Answers  

---

Explain the tensorflow?

1 Answers  

---

Explain how useful and reliable bayes’ theorem is according to you in the machine learning context?

1 Answers  

---

What is difference between deeplearning and machine learning ?

1 Answers  

---

What is rank, shape, and type in tensorflow ?

1 Answers  

---