-
TF-Slim은 텐서플로를 가볍게 사용할 수 있는 텐서플로의 확장된 추상화 라이브러리이며, 복잡한 모델을 빠르고 직관적으로 정의하고 학습할 수 있다. TF-Slim은 텐서플로 내에 포함되어 있으므로 별도의 설치를 하지 않아도 된다.
TF-Slim의 추상화는 모두 CNN에 관한 것이다. CNN의 경우 동일한 Convolution Layer을 여러번 재…
-
in network_defenition
```
import tf_slim as slim
with slim.variable_scope.variable_scope("ball", reuse=reuse):
```
provide error
`module 'tf_slim' has no attribute 'variable_scope'
`
ghost updated
7 months ago
-
authors, thanks for opensourcing your code.
I would like to know why did you choose tf.contrib.slim instead of tf.layers or just tf.keras?
I'm trying to reimplement your using tf.keras which could b…
-
`tf_slim` is used in the source code but is not listed in `requirements.txt`
-
I converted a resnet caffe model to tensorflow model. Are the pre-trained model weights compatible with tf-slim resnet ? If not, any suggestions on how to make the caffe model weights compatible with …
-
# Prerequisites
- [x] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
- [x] I am reporting the issue to the correct repository. (Model Garden official or research directory)
…
-
-
I am doing quantization aware training for Mobilenetv2 using TF Slim (TF - 1.15).
For the full model (without quantization) I get an accuracy of 80% with 1200 steps while the quantization aware tra…
kg512 updated
3 years ago
-
https://nicehjia.me/blog/2017/07/02/tensorflow-use-tf-slim/
-
@hizhangp
net = tf.pad(images, np.array([[0, 0], [3, 3], [3, 3], [0, 0]]), name='pad_1')
net = slim.conv2d(net, 64, 7, 2, padding='VALID', scope='conv_2')
I don't understand why the tf.pad was add…