Training with other configurations.

[mkocabas]

Hi @GengDavid,

Thanks for the great implementation. I'm eager collaborate with you to test other configurations. I have 2 x 1080 and 2 x 1080ti. I can borrow more if needed. Looking forward to your response!

[Tiamo666]

I just test on the model of epoch35 with ground Truth, it seems to get a little higher performance: Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.744 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.924 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.816 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.712 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.791 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.772 Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.932 Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.834 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.739 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.824

[GengDavid]

@Tiamo666 Thanks! So the number of the epoch is the point.

[mingloo]

@GengDavid @Tiamo666

I've trained the CPN101-384x288 model from scratch. The model can be downloaded from GoogleDrive.

The evaluation result is as follows:

Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets= 20 ] = 0.740
Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets= 20 ] = 0.924
Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets= 20 ] = 0.815
Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.710
Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.787
Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 20 ] = 0.770
Average Recall     (AR) @[ IoU=0.50      | area=   all | maxDets= 20 ] = 0.934
Average Recall     (AR) @[ IoU=0.75      | area=   all | maxDets= 20 ] = 0.832
Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.736
Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.822

[Tiamo666]

@mingloo great job! Could you please tell me that how many epoch did you take?

[mingloo]

@Tiamo666 I trained the CPN101-384x288 model from scratch on single 1080ti GPU with epoch=32. One key difference is the batch_size is set to 18.

And it takes almost 9 days for training from scratch.

One more thing to be noted is I use the GT bbox for training the above model.

[Tiamo666]

@mingloo Thanks a lot, I got it.

[mingloo]

@Tiamo666 Sorry. I've double checked the CPN101-384x288 model that trained from scratch is using default parameter setting. So please ignore the previous https://github.com/GengDavid/pytorch-cpn/issues/3#issuecomment-429255059.

[GengDavid]

@mingloo Thanks a lot. Wonder that have you tested trained model on different epochs or just the last epoch(32)?

[mingloo]

@GengDavid What I've tested is all for epoch=32.

[Liz66666]

@GengDavid Hi, I have meet some problems about training....... Can you share your log file about ResNet 50+256x192? Thanks

[GengDavid]

@YoungZiyu Sure, you can find training log here

[leonshek]

@Tiamo666 @GengDavid How to use the models to test one single image? Is there any inference script?

[my-hello-world]

@GengDavid @aidarikako @mingloo
hello,why i got so large loss like:

    Total params: 104.55MB

Epoch: 1 | LR: 0.00050000
iteration 100 | loss: 362.8368835449219, global loss: 246.98593711853027, refine loss: 115.85093688964844, avg loss: 403.03418150042546

i has changed lr=1e-6,but not helps. any advice?tks

[my-hello-world]

@GengDavid @mkocabas @Tiamo666 @mingloo @YoungZiyu hello,why i got so large loss like:

    Total params: 104.55MB

Epoch: 1 | LR: 0.00050000
iteration 100 | loss: 362.8368835449219, global loss: 246.98593711853027, refine loss: 115.85093688964844, avg loss: 403.03418150042546

i has changed lr=1e-6,but not helps. any advice?tks