google-deepmind / google-deepmind/kinetics-i3d

what are input_arrays and output_arrays for the model

Open
#69 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.8k
Forks
467
PR merge metrics
No merged PRs in 30d

Description

hi. iam trying to export the model into tensorflow lite but i don't know what are the input_arrays and output arrays required for the conversion method
converter = tf.lite.TFLiteConverter.from_frozen_graph(
graph_def_file, input_arrays, output_arrays)
one more issue how can i save the model from a module as tflite. I am getting a graph error all the time
m = hub.Module("https://tfhub.dev/deepmind/i3d-kinetics-400/1")
INPUT_SIZE = (None, 224, 224, 3)
model = tf.keras.Sequential([
hub.KerasLayer(m,output_shape=[400], dtype=tf.float32, trainable=False),
tf.keras.layers.Dropout(rate=0.2)
])

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.