Semantic-Segmentation
Semantic-Segmentation copied to clipboard
I will upload many semantic segmentation models to this repository for you to learn
我运行SegNet_ResNet代码时,报:ValueError: Error when checking input: expected input_1 to have 4 dimensions, but got array with shape (1, 512, 512)错误,我是按照你视频里的教学来的
在Semantic-Segmentation/Muiti_Class_deeplab_Mobile/train.py这个文件下的第六十行是什么写法???
您好,我在运行Unet-Mobile网络中的train.py文件时出现如下报错,请问您知道时什么原因嘛 ``` Deprecated in favor of operator or tf.math.divide. Epoch 1/50 Traceback (most recent call last): File "E:/Graduation_Project/Unet/train.py", line 126, in callbacks=[checkpoint, reduce_lr, early_stopping]) File "D:\Anaconda3\envs\test\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper...
出现Unresolved reference 'DepthwiseConv2D' 情况,我的环境是py36,tensorflow-gpu1.10.0,keras2.1.3
调用不了gpu
你好,我用你的Keras 搭建自己的语义分割模型里的代码运行,调用不了GPU,我是NVIDIA GeForce RTX 3050 ,安装的python:3.6,tensorflow version: 2.4.0 ,keras:2.4.3。
train过程出错
File "D:/untitled2/Segmentation/unet_mobile/train.py", line 42, in generate_arrays_from_file one_hot_label = np.eye(NCLASSES)[np.array(label, np.int16)] IndexError: index 128 is out of bounds for axis 0 with size 2 做的是2分类 但是这个地方显示128是为什么呀 求up主指导
您好,我使用deeplab-mobilenetv2模型自己的模型过拟合了,请问有什么办法吗
您好, 参照您的segnet, 斑马线上没问题,可以有效训练+预测,甚至网上抓的图片也能成功预测。 因此,用自身影像以labelme label后(0:bk 1:target) , 将jpg, png置于./dataset2/jpg 及./dataset2/png 后,开始run train.py... 出现error [https://prnt.sc/r57q5l](url) File "", line 27, in generate_arrays_from_file IndexError: too many indices for array 相关档案于此,可否请您协助剖析。万分感谢! [https://drive.google.com/file/d/1RlgNxoIwhJj0liYarbQVZEn8397tQ_PL/view?usp=sharing](url)
ValueError: Shape must be rank 3 but is rank 4 for '{{node deeplabv3plus/concatenate_1/concat}} = ConcatV2[N=2, T=DT_FLOAT, Tidx=DT_INT32](deeplabv3plus/lambda_3/resize/Squeeze, deeplabv3plus/activation_8/Relu, deeplabv3plus/concatenate_1/concat/axis)' with input shapes: [104,104,2], [?,104,104,48], []. 环境keras-gpu 2.4.3