'How do I use pretrained 'noisy_student' weights in my efficientnetv2b0 model?
I am creating an EfficientNetV2B0 model and want to use the pretrained noisy-student weights.
from tensorflow.keras.applications import EfficientNetV2B0
efficient_net = EfficientNetV2B0(weights='noisy-student', input_shape=(INPUT_SIZE, INPUT_SIZE, 3), include_top=False, pooling='max')
However, this does not work and I get the following error:
ValueError: The `weights` argument should be either `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded.Received: weights=noisy-student
Loading noisy-student weights worked with EfficientNetV1 model but doesnt work with EfficientNetV2. What can I do to fix this issue?
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|