Comments (13)
@jiawensong try to filter images those have zero bbox, by the way, can you train PASCAL VOC successfully?
from ssd.tensorflow.
I think we met the same problem. I use my own dataset which followed by the VOC format, and convert was fine (I think, cause I ran 'inspect' after, and train samples, val samples it matches). But when I train the model, the error occurs. I also received this 'InvalidArgumentError (see above for traceback): flat indices[30, :] = [30, -1] does not index into param (shape: [32,6792]).' If you solve this, could you please help me.
from ssd.tensorflow.
@franklu323 did you change your batch_size? Hope you can check if there is images that have no bbox with them, And also thanks for you issue report.
from ssd.tensorflow.
@HiKapok i can train ,test,eval,pascal successfully. I have checked all my own data, the minimum size is 3kb, contains more than one boundingbox. i wonder if the problem is that i haven't create negative boundingbox in my own data.
from ssd.tensorflow.
@HiKapok I do change my batch size to 4, cause my GPU is GTX1060 and I also change the number of classes to 5 (cause I only have 5 classes). BTW, all my dataset contains object
And I saw #12 , I also change scafford to None, but it seems got same error
from ssd.tensorflow.
@franklu323 did you also used tensorflow1.4?
from ssd.tensorflow.
@jiawensong what did you mean by 'haven't create negative boundingbox', did you have one class for background?
from ssd.tensorflow.
@HiKapok i have just create two class, number and chinese character, i haven't create class for background
from ssd.tensorflow.
@jiawensong @franklu323 both of your problems should caused by this line of code when there is image's 'batch_n_neg_select' equals 0, this only can be caused by the zero positives, so I guess there maybe some image have no bbox with them
from ssd.tensorflow.
@jiawensong background class is needed in any detection task
from ssd.tensorflow.
@HiKapok oh, maybe the problem is that i set number class with 0 label, then the program take number class as negative example, when some xml files without chinese character taken as input , the number of positive example is set to 0 and batch_n_neg_select equals 0.
from ssd.tensorflow.
@HiKapok So do I need to label the background or just in data_common.py, set background as 0 and the rest of them are my own data classes??
from ssd.tensorflow.
@franklu323 @jiawensong you needn't label background class, just follow the original pascal dataset's setting, leave one placeholder of value '0' for background class, thanks for your issue report
from ssd.tensorflow.
Related Issues (20)
- Is the coordinate position of the detection box upper left corner, lower right corner or upper left corner with width and height?
- How can I use multi-GPUs to train the ssd model? HOT 1
- the pixel of train_image_size is 256
- InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error: Assign requires shapes of both tensors to match. lhs shape= [1,1,1024,1024] rhs shape= [1,1,4096,4096] [[node save/Assign_29 (defined at E:\Infrared_Deeplearning\SSD-AbsoluteCoord\utility\scaffolds.py:86) ]] HOT 2
- 为什么开始训练后执行到一定情况就会卡住,然后CPU占用率满,但是gpu为0 HOT 1
- 为什么多GPU并行报OOM
- Why there are no celoss ,locloss and loss images after I finish training on my own dataset?
- 请问如何在GPU上运行? HOT 1
- How to train my own
- How to train my own Dataset? HOT 1
- How to continue the last training? HOT 1
- eval_ssd.py 生成的预测结果文件中没有filename HOT 1
- TypeError: Expected binary or unicode string, got None
- may i have a script for transferring .ckpt to .pb
- Hello, can this network run under win10 + CPU environment?
- 请问我在执行eval——
- 请问我在执行eval_ssd.py遇到的问题,下面是报错内容
- voc_eval.py 211行出现keyerror: File "voc_eval.py", line 211, in voc_eval R = class_recs[image_ids[d]] KeyError: '000000117121' HOT 3
- 怎样把Tensor转换成NDArray
- tensorflow.python.framework.errors_impl.NotFoundError: Could not find directory
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ssd.tensorflow.