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.

Explain the working of roc curve?

1 Answers  

---

What is the difference between tensor.eval() and session.run()?

1 Answers  

---

What are the api's used inside the tensorflow project?

1 Answers  

---

What is difference between tensorflow and pytorch ?

1 Answers  

---

How can you implement LSTM network in tensorflow ?

1 Answers  

---

What are tensor cores?

1 Answers  

---

What are the benefits of tensorflow over other libraries? Explain.

1 Answers  

---

How many layers in CNN ? How they mean ?

1 Answers  

---

What is tensorflow mobile?

1 Answers  

---

How can you implement RNN in Tensorflow ?

1 Answers  

---

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

1 Answers  

---

What are the advantages of using Tensorflow?

1 Answers  

---