issues
search
lsh1994
/
keras-segmentation
Get started with Semantic Segmentation based on Keras, including FCN32/FCN8/SegNet/U-Net
166
stars
55
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
使用fcn8模型，验证集上精度最高只有0.62
#21
richenyunqi
closed
1 year ago
0
如何使用
#20
Wei-Wu233
closed
1 year ago
0
LoadBatched.py中的getImageArr
#19
soccermom123
closed
1 year ago
0
utils.py在图片格式为 (channels, height, width)下如何修改
#18
nehSgnaiL
closed
4 years ago
0
Segnet 不加载权重的情况下可否用于灰度图像的分割？
#17
WuGe0424
closed
1 year ago
0
The result is strange.
#16
sanersbug
closed
1 year ago
0
add utils tensorflow CPU version
#15
kongnuonuo
closed
5 years ago
0
您好，请教一下utils.py的问题
#14
kongnuonuo
closed
1 year ago
4
你好，我想请问一下，想要训练自己得数据集，做2分类，需要修改那些呢？
#13
YangBai1109
closed
5 years ago
0
how to calculate meanIoU
#12
Ekinkit
closed
5 years ago
1
why is stopping int the "Epoch 1/500"?
#11
zuhaoya
closed
1 year ago
1
关于unet无法准确预测问题
#10
Niccccci
closed
1 year ago
4
u-net的decode部分
#9
lius0-0
closed
1 year ago
3
您好！请问数据集的标签为什么是黑白的？
#8
xizhouW
closed
5 years ago
0
hello i hade this error : ValueError: You are passing a target array of shape (2, 53824, 1) while using as loss `categorical_crossentropy`. `categorical_crossentropy` expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via: ``` from keras.utils.np_utils import to_categorical y_binary = to_categorical(y_int)
#7
hired-idir
closed
5 years ago
0
hello
#6
hired-idir
closed
5 years ago
0
在FCN8模型中有一点小问题：为什么模型最终输出的shape是 （-1, nClasses）。
#5
KaiiZhang
closed
1 year ago
8
problem about dataset
#4
unrealMJ
closed
5 years ago
1
getSegmentationArr 读取
#3
ShaneShen
closed
5 years ago
1
如何修改成二分类
#2
gugudexiatian
closed
5 years ago
1
如何修改为tensorflow-gpu
#1
hello1010101010101world
closed
5 years ago
3