'How to save and load model with tf.gradienttape in tenworflow2

I am using tf.gradienttape for model training and it is successful to save checkpoints for every epoch.

with train_summary_writer.as_default():
  with tf.summary.record_if(True):
    for epoch in range(epochs):
      for train_id in range(train_start_id, train_end_id):
          batch_data_path= train_data_path + 'train_data_' + str(train_id).zfill(6) + ".npy"
          batch_data = np.load(data_path)
          batch_data = np.transpose(batch_data, (0, 2, 3, 1))
          x_inp = np.reshape(np.asarray(batch_data), [-1, 5, 5, 5, 3])
          train(loss, model, opt, x_inp)

          loss_values = loss(model, x_inp)
          reconstructed = np.reshape(model(x_inp), [1, sensor_n, sensor_n, scale_n])
          # if int(train_id) % 2000:      
          tf.summary.scalar('loss',loss_values, step = train_id)
          tf.summary.image('original', tf.reshape(x_inp, (step_max, sensor_n, sensor_n, scale_n)), max_outputs=10, step=train_id)
          tf.summary.image('reconstructed', reconstructed, max_outputs=10, step=train_id)
          print("Epoch: {}  /////   Step: {}/{} ===========================> Loss: {} ".format(epoch, train_id, train_end_id, loss_values))
      save_path = manager.save()
      print("Saved checkpoint for epoch {}: {}".format(epoch, save_path))
      print("loss : {}".format(loss_values.numpy()))

Two following questions, 1. How can I save this model? 2. How can I load this model later on?

My model is kind of auto-encoder typed model, so it is necessary to create reconstructed model to compare and see errors.

Solution 1:^[1]

Save and load the model using load_model API.

model.save(model_path)

and

loaded = tf.keras.models.load_model(model_path)

check this tensorflow tutorial

Solution 2:^[2]

This guide may help: https://www.tensorflow.org/guide/saved_model

tf.saved_model.save(model, "Path")

Solution 3:^[3]

if (epoch + 1) % 10 == 0:  # Change the frequency for model saving, if needed
    if g_val_loss_f < BEST_VAL_G_LOSS: # BEST_VAL_G_LOSS=50, assign some high value initially
        BEST_VAL_G_LOSS = g_val_loss_f
        model.save("model" + str(epoch + 1) + ".h5")
    else: None

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution	Source
Solution 1	Suraj Rao
Solution 2	Suraj Rao
Solution 3	R S

'How to save and load model with tf.gradienttape in tenworflow2

Solution 1:[1]

Solution 2:[2]

Solution 3:[3]

Sources

Related Questions

Solution 1:^[1]

Solution 2:^[2]

Solution 3:^[3]