taki0112 SENet-Tensorflow issues

taki0112 / SENet-Tensorflow

Simple Tensorflow implementation of "Squeeze and Excitation Networks" using Cifar10 (ResNeXt, Inception-v4, Inception-resnet-v2)

MIT License

757 stars 269 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

can just add squeeze_abode _layer in residual connection?

#18 tanjia123456 opened 3 years ago
1
Test acc on cifar10

#17 rederyang opened 3 years ago
0
training and test data normalization

#16 Yuranus opened 5 years ago
0
Result

#15 navy63 opened 5 years ago
1
Can it support Tensorflow 2.0 with Windows10?

#14 QQ2737499951 opened 5 years ago
0
About the structure of SENet

#13 N-Kingsley opened 5 years ago
0
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 hejiemath opened 5 years ago
1
training accuracy and test accuracy is always too low

#11 JunjieZhouwust opened 5 years ago
0
How to run the code?

#10 XuXuanhui closed 5 years ago
0
how to run the classification with unseem image (se_inception_resnet_v2 )

#9 leowang7 closed 6 years ago
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 Zzzzy411 opened 6 years ago
0
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 Flatheadman closed 6 years ago
1
new dataset

#6 HanYuanyuaner opened 6 years ago
3
Is there pretained model for downloading?

#5 samsun639 opened 6 years ago
0
nan output

#4 HanYuanyuaner opened 6 years ago
2
The generated graph is degenerate

#3 akanimax opened 6 years ago
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 cchantra opened 6 years ago
1
se should be added after inception block, right?

#1 dpcross opened 6 years ago
4