sbrl-github/research-rainfallradar
1
0
Fork 0
mirror of https://github.com/sbrl/research-rainfallradar synced 2024-07-04 12:14:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

ai: add dummy label

Browse source
This commit is contained in:
Starbeamrainbowlabs 2022-09-01 17:01:00 +01:00
parent 17d42fe899
commit f1d7973f22
Signed by: sbrl
GPG key ID: 1BE5172E637709C2
2 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
aimodel/src/lib/ai/components/LayerContrastiveEncoder.py
View file

@ -52,8 +52,8 @@ class LayerContrastiveEncoder(tf.keras.layers.Layer):
# super().build(input_shape=input_shape[0]) # super().build(input_shape=input_shape[0])
# self.embedding.build(input_shape=tf.TensorShape([ *self.embedding_input_shape ])) # self.embedding.build(input_shape=tf.TensorShape([ *self.embedding_input_shape ]))
def call(self, input_thing): def call(self, input_thing, training=False):
result = self.encoder(input_thing) result = self.encoder(input_thing, training=training)
# The encoder is handled by the ConvNeXt model \o/ # The encoder is handled by the ConvNeXt model \o/
# shape_ksize = result.shape[1] # shape_ksize = result.shape[1]

3
aimodel/src/lib/dataset/dataset.py
View file

@ -1,7 +1,6 @@
import os import os
import math import math
import json import json
from socket import if_nameindex
from loguru import logger from loguru import logger
@ -28,7 +27,7 @@ def parse_item(item):
# TODO: The shape of the resulting tensor can't be statically determined, so we need to reshape here # TODO: The shape of the resulting tensor can't be statically determined, so we need to reshape here
# TODO: Any other additional parsing here, since multiple .map() calls are not optimal # TODO: Any other additional parsing here, since multiple .map() calls are not optimal
return rainfall, water return ((rainfall, water), tf.ones(1))
def make_dataset(filenames, compression_type="GZIP", parallel_reads_multiplier=1.5, shuffle_buffer_size=128, batch_size=64): def make_dataset(filenames, compression_type="GZIP", parallel_reads_multiplier=1.5, shuffle_buffer_size=128, batch_size=64):
return tf.data.TFRecordDataset(filenames, return tf.data.TFRecordDataset(filenames,