search

610265158 / mobilenetv3_centernet

A tensorflow implement mobilenetv3 centernet, which can be easily deployeed on android(MNN) and ios(CoreML).
70 stars 13 forks source link

Training hardware list? #3

Open zhousaYolo opened 4 years ago

zhousaYolo commented 4 years ago

When I use 1080ti, the parameter batchsize = 16, on the coco data set, I can't restore your training results.

610265158 commented 4 years ago

Do you mean you trained the model, but the result is not well? what is your map then?

zhousaYolo commented 4 years ago

Yes ,The Total loss is about 2.8.Can't converge.

610265158 commented 4 years ago

For mscoco, the final loss with mbv3 is about 3. 5 , there should be something wrong. Please open vis config, to check the data

zhousaYolo commented 4 years ago

Thank you! Do you mean that for mscoco dataset, the total loss of final training is about 3.5, so it can be considered as convergence? its map@0.5 Can it be accurate to 0.4? I mistakenly think that the total loss should be less than 1 before it is considered to be convergent and can be evaluated.

In addition, if you use shufflernet as backone, can it converge? map@0.5 How much is it?

zhousaYolo commented 4 years ago

I use your “ detector.pb ", testing the small mscoco data set (6 pictures), it is found that objects can be detected, but in calculating the map value, it is all 0. What's the reason?

Accumulating evaluation results...

DONE (t=0.00s).

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000

Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000

Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000

Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000

Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000

Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000

Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000

Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000

Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000

Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000

Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000

Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000

610265158 commented 4 years ago

Better do visulization the result first,
Make the json as cocostyle, and in the right category.