Tensorflow Warrior questions

Tensorflow Warrior answers

• ValueError: No gradients provided for any variable: ['conv2d/kernel:0', 'conv2d/bias:0', 'conv2d_1/kernel:0', 'conv2d_1/bias:0',
• Tensorflow (.pb) format to Keras (.h5)
• Tensorflow 2.0 list_physical_devices doesn't detect my GPU
• With ResNet50 the validation accuracy and loss is not changing
• Why does Keras gives me different results between model.evaluate, model.predicts & model.fit?
• Understanding how to use tf.dataset.map()
• Is it still necessary to implement `compute_output_shape()` when defining a custom tf.keras Layer?
• indices[201] = [0,8] is out of order. Many sparse ops require sorted indices.Use `tf.sparse.reorder` to create a correctly ordered copy
• Which numpy versions are compatible with Tensorflow 1.14.0
• Using tf.keras.utils.Sequence with model.fit_generator with use_multiprocessing=True generated warning