Alena Repina

Please try passing `dtype=tf.float32` to `hub.KerasLayer()`, i.e. ``` import tensorflow as tf import tensorflow_hub as hub IMAGE_SIZE = (224,224) class_names = ['cat','dog'] tf.keras.mixed_precision.set_global_policy('mixed_float16') model_handle = "https://tfhub.dev/google/imagenet/resnet_v1_50/feature_vector/5" do_fine_tuning = False print("Building...

Please follow the tutorial https://www.tensorflow.org/hub/tutorials/tf2_image_retraining and let us know if you still see quality issues.