yingkaisha/keras-unet-collection
The Tensorflow, Keras implementation of U-net, V-net, U-net++, UNET 3+, Attention U-net, R2U-net, ResUnet-a, U^2-Net, TransUNET, and Swin-UNET with optional ImageNet-trained backbones.
PythonMIT
Issues
- 2
vnet_2d: Inputs have incompatible shapes. Received shapes (32, 32, 512) and (32, 32, 256)
#45 opened by mehran66 - 0
ASPP block error in resunet_a_2d
#69 opened by Raito03 - 0
TypeError: unsupported operand type(s) for //: 'NoneType' and 'int' for transunet_2d and SWIN Unet
#68 opened by sm-potter - 1
UNET 3plus not learning on large datasets
#41 opened by jrmathew1 - 0
Which dimension in prediction array is the final output on U2-Net and U-Net 3+?
#66 opened by vincentallen852 - 0
- 1
How to use the exemple given using Unet3p on Oxford Pet dataset with a dataset containing gray images
#61 opened by hubsilon - 0
model_Unet_plus_plus = models.unet_plus_2d((256, 256, 1), filter_num=[32,64,128,256,512],
#62 opened by neeldesai123 - 1
- 1
ResourceExhaustedError: Swin Unet
#50 opened by Tarandeep97 - 1
Issue with using TPU of Unet model
#57 opened by yashchks87 - 0
- 2
Add new activation functions
#56 opened by mehrdad-dev - 0
Base Swin Unet and Trans UNET
#55 opened by Tombery1 - 0
Unet3+ filter_num_aggregate
#54 opened by Tombery1 - 1
- 0
how to use lambda layer rebulid the input?
#53 opened by 1183710222 - 0
Using "model.fit_generator" didn't work
#51 opened by alqurri77 - 2
ValueError: Input 0 is incompatible with layer model_1: expected shape=(None, 512, 512, 3), found shape=(None, 512, 512, 64)
#47 opened by akaiml - 1
Issues running these models on TPU
#49 opened by juanlp - 0
Attention U-Net on multiple classes
#48 opened by Tarandeep97 - 0
patch size on TransUNet
#46 opened by L007 - 0
Exemple 3 in the user guide
#44 opened by St-Savin - 1
- 2
- 6
filter_num in TransUNet
#36 opened by parniash - 1
- 1
size matter
#38 opened by soheilmajidi - 1
"NameError: name 'keras' is not defined" when loading model weights (transunet, swin-unet)
#39 opened by bsariturk - 0
hello ,
#37 opened by soheilmajidi - 3
- 15
transunet_2d
#24 opened by fatihnurcin - 3
how to use more than 3 channel input
#35 opened by rezadarooei - 3
Patch Embedding Dimension in TransUNet
#34 opened by parniash - 2
input output issue
#33 opened by soheilmajidi - 4
configuration for more deep model
#25 opened by MiladGhorbaniG - 1
关于模型文件
#28 opened by MickelZhang - 2
how to use u_net model on grayscale images
#30 opened by rezadarooei - 3
how to visualize layers
#31 opened by rezadarooei - 1
transunet训练后的模型load的时候出问题
#27 opened by danyaozou - 1
Preprocessing in examples
#29 opened by georgedeath - 0
transunet_2d
#26 opened by mbonyani - 1
saving model error
#23 opened by LiyingChan - 5
- 1
Need Dropout Layer in UNet and UNet++
#22 opened by yudshj - 4
Multiclass input
#20 opened by marcodelmoral - 6
Model saving issue for TransUNET
#18 opened by atgc1984 - 1
error on my dataset for unet3+
#19 opened by rosemolthomas30 - 3
- 1
"freeze_backbone" as RHS for both "freeze_backbone" and "freeze_batch_norm" arguments
#16 opened by ironhide23586