search

tusen-ai / simpledet

A Simple and Versatile Framework for Object Detection and Instance Recognition
Apache License 2.0
3.08k stars 488 forks source link

The results of validating a model which training with tridentnet_r101v2c4_c5_multiscale_addminival_3x_fp16.py are bad. #327

Open zhayanli opened 4 years ago

zhayanli commented 4 years ago

Describe the bug Thanks for your excellent work！ I trained my own dataset using tridentnet. I converted my dataset to coco and ran create_coco_roidb.py , then changed gpus, num_class,log_frequency to 50,loader_worker to 4 in tridentnet_r101v2c4_c5_multiscale_addminival_3x_fp16.py. Do I need to change another parameters? I trained 10 epochs and used detection_test.py to validate. The results are bad.

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.001 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 ] = 0.001 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.028 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.075 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.087 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.033 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.072 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.092

    I recorded RpnL1,RcnnL1 and Lr during the training. Could you help me, thank you!

image image image

Software info driver, CUDA, cuDNN versions OS verison My Software info is Ubantu 16.04,CUDA 10.0,cuDNN 7.4.2

How did you set up your MXNet for SimpleDet

Additional context Add any other context about the problem here.

dongjuns commented 4 years ago

How many images do you have? for training and test.

zhayanli commented 4 years ago

50 thousands for training and 5 thousands for test

dongjuns commented 4 years ago

Thanks, and how many labels are in your training dataset?

zhayanli commented 4 years ago

90 thousands labels for 18 classes.

RogerChern commented 4 years ago

Could you please kindly share a part of your annotation and the prediction json files?

On Wed, Jun 17, 2020 at 10:15 AM zhayanli notifications@github.com wrote:

90 thousands labels for 18 classes.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/TuSimple/simpledet/issues/327#issuecomment-645105527, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABGODH3BPON6DG4EACAEQ5LRXARK7ANCNFSM4NFV442Q .