timctho / Shufflenet V2 Tensorflow
Tensorflow ShuffleNet v2 implementation
Stars: ✭ 62
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Shufflenet-v2-tensorflow
Tensorflow implementation of ECCV 2018 paper ShuffleNet V2. [Paper]
Support architectures
- ShuffleNetV2 with 0.5, 1.0, 1.5, 2.0 channel multipliers
Usage
import tensorflow as tf
from net import ShuffleNetV2
if __name__ == '__main__':
# Create input placeholder
input = tf.placeholder(dtype=tf.float32, shape=[None, 224, 224, 3])
# Create model
model = ShuffleNetV2(input, 1001, model_scale=1.0, is_training=True)
# Get model inference result
print(model.output) # shape = [None, 1001]
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].