ghoshaw

AssertionError: AbstractConv2d Theano optimization failed

12

I have been through the error of #1, and solved follow the answer. but, I come to a new error as follows: AssertionError: AbstractConv2d Theano optimization failed: there is no...

How to do validation after some train steps automatically?

3

Hi， I want to add validation in your train.py in yolov3. So I will know when the network is overfitting.... So, what I need is just add a valid_step func...

Can you add "An Improved One millisecond Mobile Backbone" (MobileOne)

5

As above

 Hi， I got this error when I use sshfs-gui, I brew install sshfs, and macos is catalina.

训练完10个epoch在val的时候卡住了

2

你好，我用nanoplus训练检测，但是在val的时候卡住了， [NanoDet][12-28 08:46:55]INFO:Train|Epoch10/300|Iter8400(714)| lr:9.98e-04| loss_qfl:0.2423| loss_bbox:0.2495| loss_dfl:0.1563| aux_loss_qfl:0.2187| aux_loss_bbox:0.2325| aux_loss_dfl:0.1512| [NanoDet][12-28 08:47:59]INFO:Train|Epoch10/300|Iter8450(764)| lr:9.98e-04| loss_qfl:0.2119| loss_bbox:0.2754| loss_dfl:0.1546| aux_loss_qfl:0.1929| aux_loss_bbox:0.2523| aux_loss_dfl:0.1503| [NanoDet][12-28 08:48:58]INFO:Train|Epoch10/300|Iter8500(814)| lr:9.98e-04| loss_qfl:0.2317| loss_bbox:0.2438| loss_dfl:0.1465| aux_loss_qfl:0.2036| aux_loss_bbox:0.2194| aux_loss_dfl:0.1404| [NanoDet][12-28 08:49:51]INFO:Val|Epoch10/300|Iter8539(0)|...

HI, How to train superpoint with rgb input? Directly change the gray to rgb, some errors happens in image aug part.

Hi, if run this model in mobile use ncnn or coreml, can it run in real-time?

Hi, I run the demo as README. I install the vtk and I am sure that 'vtkOpenGLKitPython.so' is in /usr/local/lib/python3.5/dist-packages/vtk/ folder. but still got the error as mentioned above.

about the data

1

Hi, could you please release the data list of gld after your cleaning?

你好，我想问下我在正常的训练过程中，改了数据读取模块，为什么直接就生效了呢，然后本来正在运行的代码会在我改的地方报错了，因为我改动了输入size。为什么这个会实时更新锕，这个设置怎么关掉呢？