fangxu
fangxu
![image](https://user-images.githubusercontent.com/16681534/118192752-33eacb00-b479-11eb-96c6-d5c51cb37291.png) `We may apply a series of transformations .....` what's the transformations ? Can we view transformation as convolution module ?
like trajectory and error plot in one image
how to make this curve ? ![image](https://user-images.githubusercontent.com/16681534/95673563-2ff18480-0bdc-11eb-8991-4187781f95da.png)
Dear @bittnt , During training my CRFasRNN model, when I entered the command: python ../fcn.berkeleyvision.org/voc-fcn8s-atonce/solve.py This problem has occurred ``` I0705 20:45:21.787677 25165 net.cpp:111] Creating Layer inference1 I0705 20:45:21.787684 25165...
``` [sensetime@localhost ~]$ sudo pip install opencv-python==3.2.0.6 [sudo] password for sensetime: Collecting opencv-python==3.2.0.6 Using cached opencv_python-3.2.0.6-cp27-cp27mu-manylinux1_x86_64.whl Requirement already satisfied: numpy>=1.11.3 in /usr/lib64/python2.7/site-packages (from opencv-python==3.2.0.6) Installing collected packages: opencv-python Successfully installed...
``` [sensetime@localhost mxnet]$ git submodule update fatal: reference is not a tree: 89de7ab20167909bc2c4f8acd397671c47cf3c0d Unable to checkout '89de7ab20167909bc2c4f8acd397671c47cf3c0d' in submodule path 'cub' ``` I don't know why it's like this
这个 地方如果是class_caps 类型,这个地方的地方是否应该修改 为 修改代码 ``` if w_shared: hw = int(B / w.size(1)) w = w.repeat(1, hw, 1, 1, 1) else: w = w.repeat(b, 1, 1, 1, 1) ```` 原代码...
在网络模型的输入中没有发现类别label 信息的载入?太奇怪了,这样自己做一个数据集和修改都不知道从何处 下手。 现在我能把数据集做成 json 文件格式的样子,能够包含起始位置,类型信息等。可以指没看见label类别信息的映射~帮忙指点一下,按照我的理解。比如activitynet 有个200类别,最后肯定有一个分类模块。并且输入输出结果映射指导类别上