taki0112/SENet-Tensorflow
Simple Tensorflow implementation of "Squeeze and Excitation Networks" using Cifar10 (ResNeXt, Inception-v4, Inception-resnet-v2)
PythonMIT
Issues
- 1
- 0
Test acc on cifar10
#17 opened by rederyang - 1
- 3
new dataset
#6 opened by HanYuanyuaner - 0
training and test data normalization
#16 opened by Yuranus - 0
- 0
About the structure of SENet
#13 opened by N-Kingsley - 1
in the resnext block, why the [1, 1] convolution has stride>1, where [3, 3] has stride 1, the downsample is realized by [3, 3] convolution with stride=2 in resnet
#12 opened by hejiemath - 0
- 2
nan output
#4 opened by HanYuanyuaner - 0
How to run the code?
#10 opened by XuXuanhui - 0
- 1
ensorflow.python.framework.errors_impl.InvalidArgumentError: Reshape cannot infer the missing input size for an empty tensor unless all specified input sizes are non-zero..'
#2 opened by cchantra - 1
Can you please suggest how much gpu memory should I use in order to complete the training? mine is a 4g gpu, and with that config set in sess, it ran out of resource every time I try. Thanks.
#7 opened by Flatheadman - 0
Question:Tried to convert 'tensor' to a tensor and failed. Error: Argument must be a dense tensor: Last layer is: DenseLayer (srgan_g5_densenet_se/SE_block1_dense2) [16, 32] - got shape [19], but wanted [].
#8 opened by Zzzzy411 - 0
Is there pretained model for downloading?
#5 opened by samsun639 - 1
The generated graph is degenerate
#3 opened by akanimax - 4