Closed ptoews closed 3 years ago
Hi @ptoews,
below you can find my answers. I hope this helps.
Q1 Padding:
Q2 Conv Layers:
import tensorflow.contrib.slim as slim
conv_square = slim.conv2d(inputs=input_element,
num_outputs=num_output,
kernel_size=[3, 3],
activation_fn=tf.nn.relu,
padding="same")
Q3 What p did you choose for the dropout layer:
Q4 Loss:
Q5 Weights (for loss) due to imbalanced data:
Q6 Weights for samples:
Q7 Learning rate:
Sorry for the late reply. If you have any further questions, please feel free to contact me.
Hi @rheinzler,
for my master's thesis I would like to compare WeatherNet with other approaches and therefore want to implement it as closely to your model as possible. However, I couldn't find information about all the hyperparameters I have to set, and wondered if you could help me with the following questions:
Thanks in advance!