Training with other configurations.
mkocabas opened this issue · 64 comments
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!
Hi @mkocabas ,
Thanks for your interest in my implementation.
There may be at least two configurations to be tested, ResNet-50+384x288
and ResNet-101+384x288
. Which one do you prefer to test? Or do you want to test both of them?
I've modified the codes a little, so please clone/pull the latest version before you run it. Please follow README
to configure the environment.
You can train a ResNet-50+384x288
model directly in 384.288.model dir. by running train.py
You may need to modify batch size in config.py
, and use -g
to specify the number of GPU you use. For example, you may set batch_size = 12
and run python3 train.py -g 2
when you use 2 x 1080 gpu to train the model.
To train a ResNet-101+384x288
model, you need to set model='CPN101'
in config.py
, and then follow the same way to train the model.
If you have any questions, feel free to contact me. You can also mail me at zhanggw8@mail2.sysu.edu.cn or zgwdavid@gmail.com.
Cool, so I can start with ResNet-50+384x288
. After that I can try ResNet-101
.
I'll use 2 x 1080ti
with the default hyperparameters as in config. Am I correct?
@GengDavid we have a little problem. 1080ti
s have 11GB memory. batch_size=6
barely fits the memory. This means that we can train with batch_size=12
using 2 gpus. What do you think?
If you are using 1080ti
s, I think you can set batch_size
more than 12 with 2 gpus while running ResNet-50+384x288
model.
@mkocabas ResNet-50+384x288
model with batch_size=12
takes about 8G memory in my experiment.
I'm consistently getting OOM error, but let me check. I'll restart the computer, maybe there are some blocking processes. I'll inform you about the progress.
@GengDavid, restarting solved the problem. Thanks for pointing out! I'll update this issue as training continues.
How many epochs did you train the 256x192
model?
I see, so probably it'll take 4 days to converge.
Fine, thanks.
Epoch 6 (tested with GT bboxes)
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.688
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.894
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.750
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.654
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.742
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.719
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.904
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.776
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.681
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.777
Epoch 13 (tested with GT bboxes)
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.726
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.914
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.785
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.690
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.781
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.754
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.924
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.810
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.716
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.812
@GengDavid do you have the weights of 5th epoch of ResNet50-256x192
model?
Yeah I saw the discussion. Please let me know about the results after modification. If you don't have enough GPUs, I can test the corrected model.
I'll let you know the results but it may take a little long time since I only have 1*1080
free to run the code. May be you can test test the ResNet-50+384x288
model first.
Thanks!
I've started to train fixed ResNet-50+384x288
on a Titan V
w batch-size=24
Hi, @mkocabas
I've updated the ResNet-50+256*192
results. Have got some results?
Thx.
Hi, David, I've trained with the ResNet-50+384*288 with ground truth bboxes.
The test result of 32 epoch is as follows:
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.737
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.915
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.806
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.706
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.792
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.767
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.929
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.826
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.729
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.824
Due to the limit of network, I can not download the person detections results on COCO successfully, So I just use the ground truth.
@Tiamo666 Great job!
Can you provide the pre-trained model so that I can test it with detection results?
I think you can open a PR with the a link on it to download pre-trained model.
@Tiamo666 Or if you do not want to open a RP, could you just provide a link to download the model? Google Drive, Onedrive, Dropbox and Baidu Yun are all fine.
OK,I guess Baidu yun is a good choice. I will try to share the pretrained model on it and provide you the link as soon as I uploaded model
hi,David, I've already uploaded the model on BaiduYun.
Here is the link:
https://pan.baidu.com/s/1fdy5_0HQm63QtlOzxKbpuw
Great! I'll test it and update the result later.
That's cool!
I'll have time to train with Resnet101+384*288, I'll share the model after finishing training
Hi, David. I've uploaded the model of cpn384*288 with Resnet101 on Baidu Yun.
Here is the link:
https://pan.baidu.com/s/1toikUHSqHhHP3DkIOkNctA
Hello, David, I've just found that I trained with the old code which has "Color Normalized bug" last week. I feel sorry for that, I could retrain the model this week.
@Tiamo666 Retraining it is a better choice but may cost more time. I think we can just fine-tune the trained model. This may influence the result a little but can save time. However, I currently do not have free GPUs to do this work.
What do you think about that?
OK, Thank you for your advice. I think fine-tune the model is a good idea.
Another thing I wanted to mention is that in issue#7, it doesn't matter whether there is bias in nn.conv2d cause the batchnorm will minus the mean value, so plus a constant will not affect the result.
@Tiamo666 Yep, the bias has little influence to the result. However, it is better to avoid adding bias to conv2d
with batchnorm
.
@Tiamo666 Here is what I did. You can modify the training codes like this(from line 38)
if args.resume:
if isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
checkpoint_state_dict = checkpoint['state_dict']
new_dict = {}
for k,v in checkpoint_state_dict.items():
if k=='module.global_net.upsamples.0.1.bias':
continue
if k=='module.global_net.upsamples.1.1.bias':
continue
if k=='module.global_net.upsamples.2.1.bias':
continue
new_dict[k]=v
model.load_state_dict(new_dict)
args.start_epoch = checkpoint['epoch']
# optimizer.load_state_dict(checkpoint['optimizer'])
Using --resume
to continue training, and set --epochs
to one or two larger than the checkpoint you load.
(and also make sure to change the learning rate to a proper value. )
Ok, That's cool, thanks a lot.
Hello, David. I've upload the model of cpn384x288 with resnet101 On BaiduYun.
Here is the link:
https://pan.baidu.com/s/1e_meK3xnGRZXJEBaFVXB3A
Cool. @Tiamo666 Could you please tell me the results you got before and after the fine-tune process(using gt bbox)?
Hello, David, the results after fine-tune is
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.740
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.923
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.806
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.711
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 ] = 0.931
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.829
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 ] = 0.821
Before fine-tune is
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.075
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.154
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.063
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.100
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.043
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.084
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.165
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.073
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.109
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.049
@Tiamo666 Thanks! I'm a little busy these days, I'll update the results and model soon.
I've used the commit 8e85af2 to train ResNet50
+ 256x192
model with GT bbox input and default parameter setting from scratch when epoch
is set to 32 and the overall result 70.8
as below shown is slightly worse than the reported one 71.2
:
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.708
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.905
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.782
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.683
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.749
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.740
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.918
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.804
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.710
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.786
How many epochs do you set to achieve 71.2
for ResNet50
+ 256x192
?
As for ResNet50
+ 384x288
model with GT bbox input and default parameter setting training from scratch, the epoch=32
result is slightly better than the reported 73.7
as follows:
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.741
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.925
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.805
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.706
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.795
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.768
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.932
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.825
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.730
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.826
@mkocabas Sorry about that I have not updated the results yet. 71.2
is the old result.
It is strange that the results that after fixing bugs are lower than the results before. I'll update all the results this weekends, but I still do not figure out the reason. Maybe we need to adjust the parameter setting since this parameter setting is setting for the old codes.
@GengDavid Now, the ResNet 50
+ 256x192
with detection GT bboxes is slightly worse than the old result, but the ResNet 50
+ 384x288
is slightly better than the old result.
Cool, so I think it is allowable to have some slight differences. And could you provide your pre-trained ResNet 50 + 384x288
with us? It would be great.
@GengDavid Please see my comments #3 (comment)
Sorry, I don't clearly understand what you mean by referencing comment-424928303😳
@GengDavid
Sorry, I misunderstand your comment.
The trained model for ResNet50
+ 384x288
can be found at GoogleDrive.
However, it is a little confusing that the CPN-101-384x288
model perform even worse than CPN-50-384x288
.
@Tiamo666 Could you show me the parameter setting you used to fine-tune the model? Thanks!
Have a good National Day.
@GengDavid @Tiamo666 Thanks for updating the result.
I'll try to train CPN-ResNet101-384x288
from scratch on my side.
@GengDavid , Thanks a lot, I just come back from my holiday. I didn't change any other parameters, I just modified the learning rate scheduler with pytorch built-in package optim.lr_scheduler, here is my code:
fine tune
for k, v in pretrained_dict.items():
if k in ['module.global_net.upsamples.0.1.bias',
'module.global_net.upsamples.1.1.bias',
'module.global_net.upsamples.2.1.bias']:
continue
new_dict[k] = v
model.load_state_dict(new_dict)
adjust lr rate
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones = cfg.lr_dec_epoch, gamma=cfg.lr_gamma)
for epoch in range(args.start_epoch, args.epochs):
#lr = adjust_learning_rate(optimizer, epoch, cfg.lr_dec_epoch, cfg.lr_gamma)
scheduler.step(epoch)
lr = optimizer.state_dict()['param_groups'][0]['lr']
print('\nEpoch: %d | LR: %.8f' % (epoch + 1, lr))
The following is part of my log.txt, I fine tuned from epoch32, and the total epoch is 35:
30.000000 0.000031 102.073177
31.000000 0.000016 101.399609
32.000000 0.000016 101.165480
33.000000 0.000016 101.801196
34.000000 0.000016 101.328027
35.000000 0.000016 101.059933
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
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
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
Sorry. I've double checked the CPN101-384x288
model that trained from scratch is using default parameter setting. So please ignore the previous #3 (comment).
@mingloo Thanks a lot.
Wonder that have you tested trained model on different epochs or just the last epoch(32)?
@GengDavid
What I've tested is all for epoch=32
.
@GengDavid Hi, I have meet some problems about training....... Can you share your log file about ResNet 50+256x192? Thanks
@Tiamo666 @GengDavid
How to use the models to test one single image?
Is there any inference script?
@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
@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