1

I have just started TF Object Detection API two weeks ago, and manage to train a model to recognize a custom object, in my case, a Mecanum wheel.

Here's the details:

  • No. of training images = 125
  • All training images are around 500 x 500 (plus minus)
  • Transfer Learning
  • Model used = ssd_mobilenet_v1_coco
  • batch size = 2
  • total steps ran = 12715
  • loss is around 0.5000 - 2.5000, some time it fluctuate to more than 10, I am not sure why

Here's the result: The first image is encouraging.

The second image starts to disappoint me a little. I expect the model to detect FOUR (four boxes) Mecanum wheel. Why?

Then, I suspect that's there's something wrong with my trained model. I tried with the sample test images, the third image and fourth image, then I am sure that this is totally not the model I first aim for.

I have been reading this post which I think our problems are quite similar (and he manage to solve it). He mentioned that the input image needs to be less than 600 x 1024, so I tried with fifth image and unsurprisingly, the result is again disappointing.

I went through the tutorial series by sentdex and in the comment sections, I notice that there are many people face this problem too. So, what to do now?

Can someone please help me to edit the list? Why can't I make it to one paragraph one list?

mkrieger1
  • 19,194
  • 5
  • 54
  • 65
iSeeDeadPeople
  • 59
  • 8

1 Answers1

0

125 images? You will not be able to get very good results with that many images. If you want to validate that this is indeed the problem, try training with just subsets of your original 125 images.

For example, how bad is the output when you train on 10 images?

Does it get better when you use 50 images?

Does it get better yet when you use 125 images?

If the accuracy improves with increasing dataset size, you can extrapolate and guess that with 1000 images, you will be able to do even better. I would guess that that is your problem.

bremen_matt
  • 6,902
  • 7
  • 42
  • 90
  • Tested with 300 images and it improved ! Thanks. – iSeeDeadPeople Feb 06 '18 at 01:57
  • Hi, I am confused with one thing now.. What's actually test.record for? When the whole process is just about training, then why we need test.record? In this [video](https://www.youtube.com/watch?list=PLQVvvaa0QuDcNK5GeCQnxYnSSaar2tpku&v=srPndLNMMpk), he is getting images from test.record to test the newly trained model, doesn't the model already know its image from test.record? – iSeeDeadPeople Apr 03 '18 at 04:35
  • That is a separate question. I have never used the api – bremen_matt Apr 03 '18 at 05:01