mmpose
mmpose copied to clipboard
open-mmlab
[Bug] RTMO算法计算loss的gt输入是否存在问题
Prerequisite
- [X] I have searched Issues and Discussions but cannot get the expected help.
- [X] The bug has not been fixed in the latest version(https://github.com/open-mmlab/mmpose).
Environment
OrderedDict([('sys.platform', 'win32'), ('Python', '3.9.13 (main, Oct 13 2022, 21:23:06) [MSC v.1916 64 bit (AMD64)]'), ('CUDA available', True), ('MUSA available', False), ('numpy_random_seed', 2147483648), ('GPU 0', 'NVIDIA GeForce RTX 3090'), ('GPU 1', 'NVIDIA GeForce RTX 3060'), ('CUDA_HOME', 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8'), ('NVCC', 'Cuda compilation tools, release 11.8, V11.8.89'), ('MSVC', '用于 x64 的 Microsoft (R) C/C++ 优化编译器 19.34.31937 版'), ('GCC', 'n/a'), ('PyTorch', '2.0.1+cu117'), ('PyTorch compiling details', 'PyTorch built with:\n - C++ Version: 199711\n - MSVC 193431937\n - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications\n - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)\n - OpenMP 2019\n - LAPACK is enabled (usually provided by MKL)\n - CPU capability usage: AVX2\n - CUDA Runtime 11.7\n - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37\n - CuDNN 8.5\n - Magma 2.5.4\n - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=C:/actions-runner/_work/pytorch/pytorch/builder/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj /FS -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=OFF, TORCH_VERSION=2.0.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON, USE_ROCM=OFF, \n'), ('TorchVision', '0.15.2+cu117'), ('OpenCV', '4.9.0'), ('MMEngine', '0.10.3'), ('MMPose', '1.3.1+5a3be94')])
Reproduces the problem - code sample
当我使用RTMO算法进行训练自己的数据集的时候，我发现在计算loss的时候，也就是在Hybrid_heads/rtmo_head.py里面。当使用generate_targets函数的时候。传入的gt信息是原图的信息。而不是resize到640*640的关键点和bbox坐标。请问这是为什么，算错了吗？还是我理解有问题？
Reproduces the problem - command or script
python tools/train.py .\data\rtmo-s_8xb32-700e_hand-640x640.py
Reproduces the problem - error message
我的coco文件夹第一张图的关键点信息如下
当我进入Hybrid_heads/rtmo_head.py里面，也就是下面函数
然后进入yolopose_head.py里面的self._get_targets_single(）函数，通过Sim_ota进行正负样本分配，即下面位置：
我以为是在计算前进行转换，但是我分析sim_ota_assigner.py里面的assign函数拿到gt直接进行计算。
即下面位置我进行了打印
打印结果如下：
所以说是使用原图的信息进行正负样本匹配吗？
按照正常的理解不应该是resize后的图像的gt吗？
Additional information
按照正常的理解不应该是resize后的图像的gt吗？
贴一下config吧
`base = ['../configs/base/default_runtime.py']
runtime
train_cfg = dict(max_epochs=700, val_interval=1, dynamic_intervals=[(670, 1)])
auto_scale_lr = dict(base_batch_size=256)
default_hooks = dict( checkpoint=dict(type='CheckpointHook', interval=50, max_keep_ckpts=3))
optim_wrapper = dict( type='OptimWrapper', constructor='ForceDefaultOptimWrapperConstructor', optimizer=dict(type='AdamW', lr=0.004, weight_decay=0.05), paramwise_cfg=dict( norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True, force_default_settings=True, custom_keys=dict({'neck.encoder': dict(lr_mult=0.05)})), clip_grad=dict(max_norm=0.1, norm_type=2))
param_scheduler = [ dict( type='QuadraticWarmupLR', by_epoch=True, begin=0, end=5, convert_to_iter_based=True), dict( type='CosineAnnealingLR', eta_min=0.0002, begin=5, T_max=350, end=349, by_epoch=True, convert_to_iter_based=True), # this scheduler is used to increase the lr from 2e-4 to 5e-4 dict(type='ConstantLR', by_epoch=True, factor=2.5, begin=349, end=350), dict( type='CosineAnnealingLR', eta_min=0.0002, begin=350, T_max=320, end=670, by_epoch=True, convert_to_iter_based=True), dict(type='ConstantLR', by_epoch=True, factor=1, begin=670, end=700), ]
data
input_size = (640, 640) metafile = 'configs/base/datasets/hand.py' codec = dict(type='YOLOXPoseAnnotationProcessor', input_size=input_size)
train_pipeline_stage1 = [ dict(type='LoadImage', backend_args=None), dict( type='Mosaic', img_scale=(640, 640), pad_val=114.0, pre_transform=[dict(type='LoadImage', backend_args=None)]), dict( type='BottomupRandomAffine', input_size=(640, 640), shift_factor=0.2, rotate_factor=30, scale_factor=(0.5, 1.5), pad_val=114, distribution='uniform', transform_mode='perspective', bbox_keep_corner=False, clip_border=True, ), dict( type='YOLOXMixUp', img_scale=(640, 640), ratio_range=(0.6, 1.6), pad_val=114.0, pre_transform=[dict(type='LoadImage', backend_args=None)]), dict(type='YOLOXHSVRandomAug'), dict(type='RandomFlip'), dict(type='FilterAnnotations', by_kpt=True, by_box=True, keep_empty=False), dict(type='GenerateTarget', encoder=codec), dict(type='PackPoseInputs'), ] train_pipeline_stage2 = [ dict(type='LoadImage'), dict( type='BottomupRandomAffine', input_size=(640, 640), shift_prob=0, rotate_prob=0, scale_prob=0, scale_type='long', pad_val=(114, 114, 114), bbox_keep_corner=False, clip_border=True, ), dict(type='YOLOXHSVRandomAug'), dict(type='RandomFlip'), dict(type='BottomupGetHeatmapMask', get_invalid=True), dict(type='FilterAnnotations', by_kpt=True, by_box=True, keep_empty=False), dict(type='GenerateTarget', encoder=codec), dict(type='PackPoseInputs'), ]
val_pipeline = [ dict(type='LoadImage'), dict( type='BottomupResize', input_size=input_size, pad_val=(114, 114, 114)), dict(type='BottomupGetHeatmapMask', get_invalid=True), dict(type='FilterAnnotations', by_kpt=True, by_box=True, keep_empty=False), dict(type='GenerateTarget', encoder=codec), dict( type='PackPoseInputs', meta_keys=('id', 'img_id', 'img_path', 'ori_shape', 'img_shape', 'input_size', 'input_center', 'input_scale')) ]
data_mode = 'bottomup' data_root = 'D:/Hand/data/BonesOfHand_keypoint/COCODataset1/'
train datasets
dataset_crowdpose = dict(
type='HandDataset',
data_root=data_root,
data_mode=data_mode,
ann_file='train_coco.json',
data_prefix=dict(img='images/'),
pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1
)
train_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, pin_memory=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dataset_crowdpose)
val_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, pin_memory=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='val_coco.json', data_prefix=dict(img='images/'), test_mode=True, pipeline=val_pipeline, )) test_dataloader = val_dataloader
val_evaluator = dict( type='CocoMetric', ann_file=data_root + 'val_coco.json', score_mode='bbox', nms_mode='none', )
test_evaluator = val_evaluator
hooks
custom_hooks = [ dict( type='YOLOXPoseModeSwitchHook', num_last_epochs=30, new_train_pipeline=train_pipeline_stage2, priority=48), dict( type='RTMOModeSwitchHook', epoch_attributes={ 350: { 'proxy_target_cc': True, 'overlaps_power': 1.0, 'loss_cls.loss_weight': 2.0, 'loss_mle.loss_weight': 5.0, 'loss_oks.loss_weight': 10.0 }, }, priority=48), dict(type='SyncNormHook', priority=48), dict( type='EMAHook', ema_type='ExpMomentumEMA', momentum=0.0002, update_buffers=True, strict_load=False, priority=49), ]
model
widen_factor = 0.5 deepen_factor = 0.33
model = dict( type='BottomupPoseEstimator', init_cfg=dict( type='Kaiming', layer='Conv2d', a=2.23606797749979, distribution='uniform', mode='fan_in', nonlinearity='leaky_relu'), data_preprocessor=dict( type='PoseDataPreprocessor', pad_size_divisor=32, # 32 mean=[0, 0, 0], std=[1, 1, 1], # batch_augments=[ # dict( # type='BatchSyncRandomResize', # random_size_range=(480, 800), # size_divisor=32, # interval=1), # ] ), backbone=dict( type='CSPDarknet', deepen_factor=deepen_factor, widen_factor=widen_factor, out_indices=(2, 3, 4), spp_kernal_sizes=(5, 9, 13), norm_cfg=dict(type='BN', momentum=0.03, eps=0.001), act_cfg=dict(type='Swish'), init_cfg=dict( type='Pretrained', checkpoint='https://download.openmmlab.com/mmdetection/v2.0/' 'yolox/yolox_s_8x8_300e_coco/yolox_s_8x8_300e_coco_' '20211121_095711-4592a793.pth', prefix='backbone.', )), neck=dict( type='HybridEncoder', in_channels=[128, 256, 512], deepen_factor=deepen_factor, widen_factor=widen_factor, hidden_dim=256, output_indices=[1, 2], encoder_cfg=dict( self_attn_cfg=dict(embed_dims=256, num_heads=8, dropout=0.0), ffn_cfg=dict( embed_dims=256, feedforward_channels=1024, ffn_drop=0.0, act_cfg=dict(type='GELU'))), projector=dict( type='ChannelMapper', in_channels=[256, 256], kernel_size=1, out_channels=256, act_cfg=None, norm_cfg=dict(type='BN'), num_outs=2)), head=dict( type='RTMOHead', num_keypoints=21, featmap_strides=(16, 32), head_module_cfg=dict( num_classes=1, in_channels=256, cls_feat_channels=256, channels_per_group=36, pose_vec_channels=256, widen_factor=widen_factor, stacked_convs=2, norm_cfg=dict(type='BN', momentum=0.03, eps=0.001), act_cfg=dict(type='Swish')), assigner=dict( type='SimOTAAssigner', dynamic_k_indicator='oks', oks_calculator=dict(type='PoseOKS', metainfo=metafile)), prior_generator=dict( type='MlvlPointGenerator', centralize_points=True, strides=[16, 32]), dcc_cfg=dict( in_channels=256, feat_channels=128, num_bins=(192, 256), spe_channels=128, gau_cfg=dict( s=128, expansion_factor=2, dropout_rate=0.0, drop_path=0.0, act_fn='SiLU', pos_enc='add')), overlaps_power=0.5, loss_cls=dict( type='VariFocalLoss', reduction='sum', use_target_weight=True, loss_weight=1.0), loss_bbox=dict( type='IoULoss', mode='square', eps=1e-16, reduction='sum', loss_weight=5.0), loss_oks=dict( type='OKSLoss', reduction='none', metainfo=metafile, loss_weight=30.0), loss_vis=dict( type='BCELoss', use_target_weight=True, reduction='mean', loss_weight=1.0), loss_mle=dict( type='MLECCLoss', use_target_weight=True, loss_weight=1e-3, ), loss_bbox_aux=dict(type='L1Loss', reduction='sum', loss_weight=1.0), ), test_cfg=dict( input_size=input_size, score_thr=0.1, nms_thr=0.65, )) `
我也打印了输入图像的size，并且show了图像。图像就是resize到640*640的，并且保持宽高比的。但是bbox和keypoints还是原始的，你是说config不对吗？
dataset_crowdpose = dict(
type='HandDataset',
data_root=data_root,
data_mode=data_mode,
ann_file='train_coco.json',
data_prefix=dict(img='images/'),
pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1
)
训练数据集别用val_pipeline
dataset_crowdpose = dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='train_coco.json', data_prefix=dict(img='images/'), pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1 )训练数据集别用val_pipeline
看大了BottomupRandomAffine和BottomupResize的区别了。没细读代码，感谢
dataset_crowdpose = dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='train_coco.json', data_prefix=dict(img='images/'), pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1 )训练数据集别用val_pipeline
看大了BottomupRandomAffine和BottomupResize的区别了。没细读代码，感谢
你好 我在训练RTMO时发现他的loss_mle会训练成负值 为什么会这样是因为1e−4嘛 09/01 10:07:00 - mmengine - INFO - Epoch(train) [1][ 9000/16029] base_lr: 5.044198e-05 lr: 5.044198e-05 eta: 26 days, 17:51:34 time: 0.248321 data_time: 0.002521 memory: 4903 grad_norm: 75.045101 loss: 24.547811 loss_bbox: 2.699222 loss_vis: 0.458490 loss_mle: -0.017420 loss_oks: 20.619778 loss_cls: 0.787740 num_samples: 67.000000 overlaps: 0.486408
dataset_crowdpose = dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='train_coco.json', data_prefix=dict(img='images/'), pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1 )训练数据集别用val_pipeline
看大了BottomupRandomAffine和BottomupResize的区别了。没细读代码，感谢
你好 我在训练RTMO时发现他的loss_mle会训练成负值 为什么会这样是因为1e−4嘛 09/01 10:07:00 - mmengine - INFO - Epoch(train) [1][ 9000/16029] base_lr: 5.044198e-05 lr: 5.044198e-05 eta: 26 days, 17:51:34 time: 0.248321 data_time: 0.002521 memory: 4903 grad_norm: 75.045101 loss: 24.547811 loss_bbox: 2.699222 loss_vis: 0.458490 loss_mle: -0.017420 loss_oks: 20.619778 loss_cls: 0.787740 num_samples: 67.000000 overlaps: 0.486408
我训练自己的模型，mleloss也出现了负值。（我自己的数据集）。我训练的mlecc的loss权重是1，你的是1e-4吗
@Ben-Louis 大佬再请教一个问题。我使用rtmo里面的coco数据集及其coco下面的rtmo-s_8xb32-600e_coco-640x640.py配置文件进行训练，得到的最终mAP才达到0.607? 而与实际的0.677还是有很大的差异的，请问是什么原因？
我只是将batch_size由32改为了16（因为电脑配置的问题，32跑不动）。
然后我对比了backbone为s和m,l的区别。我发现就MLECCLoss的权重是1，而不是1e-3， 而且crowdpose的rtmo-s的MLECCLOSS的权重也是1e-3，所以这个是其中一个原因吗？
@Ben-Louis 最终我的训练，得到的结果如下
而使用rtmo下载的s模型的权重跑的结果如下：
感觉差异还是蛮大的呢，七个点。。所以公开的rtmo-s的训练配置问题参数有问题吗？
dataset_crowdpose = dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='train_coco.json', data_prefix=dict(img='images/'), pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1 )训练数据集别用val_pipeline
看大了BottomupRandomAffine和BottomupResize的区别了。没细读代码，感谢
你好 我在训练RTMO时发现他的loss_mle会训练成负值 为什么会这样是因为1e−4嘛 09/01 10:07:00 - mmengine - INFO - Epoch(train) [1][ 9000/16029] base_lr: 5.044198e-05 lr: 5.044198e-05 eta: 26 days, 17:51:34 time: 0.248321 data_time: 0.002521 memory: 4903 grad_norm: 75.045101 loss: 24.547811 loss_bbox: 2.699222 loss_vis: 0.458490 loss_mle: -0.017420 loss_oks: 20.619778 loss_cls: 0.787740 num_samples: 67.000000 overlaps: 0.486408
我训练自己的模型，mleloss也出现了负值。（我自己的数据集）。我训练的mlecc的loss权重是1，你的是1e-4吗
没有唉 我用的是正常的rtmo-l的config配置
@Ben-Louis 大佬再请教一个问题。我使用rtmo里面的coco数据集及其coco下面的rtmo-s_8xb32-600e_coco-640x640.py配置文件进行训练，得到的最终mAP才达到0.607? 而与实际的0.677还是有很大的差异的，请问是什么原因？
我只是将batch_size由32改为了16（因为电脑配置的问题，32跑不动）。
然后我对比了backbone为s和m,l的区别。我发现就MLECCLoss的权重是1，而不是1e-3， 而且crowdpose的rtmo-s的MLECCLOSS的权重也是1e-3，所以这个是其中一个原因吗？
batchsize是 $8 \times 32 = 256$，不是 32。你要复现的话 batchsize 得一致
@Ben-Louis 大佬再请教一个问题。我使用rtmo里面的coco数据集及其coco下面的rtmo-s_8xb32-600e_coco-640x640.py配置文件进行训练，得到的最终mAP才达到0.607? 而与实际的0.677还是有很大的差异的，请问是什么原因？ 我只是将batch_size由32改为了16（因为电脑配置的问题，32跑不动）。 然后我对比了backbone为s和m,l的区别。我发现就MLECCLoss的权重是1，而不是1e-3， 而且crowdpose的rtmo-s的MLECCLOSS的权重也是1e-3，所以这个是其中一个原因吗？
batchsize是 8 × 32 = 256 ，不是 32。你要复现的话 batchsize 得一致
@Ben-Louis 所以你这8xb32其实是8个GPU，每个gpu的batch_size是32。因此总的batch_size是256。而实际上我复现的是1xb16，是不是对应的我的学习率应该设置为lr/16，对应到config文件，应该设置auto_scale_lr = dict(base_batch_size=256/16)，这样就可以达到起码接近的效果，是这样吗？
@Ben-Louis 还有就是对于mmpose里面的 configs\body_2d_keypoint\rtmo\coco\rtmo_coco.yml
Dataset还写的是 CrowdPose，这个可以修改一下呢。容易误导
dataset_crowdpose = dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='train_coco.json', data_prefix=dict(img='images/'), pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1 )训练数据集别用val_pipeline
看大了BottomupRandomAffine和BottomupResize的区别了。没细读代码，感谢
你好 我在训练RTMO时发现他的loss_mle会训练成负值 为什么会这样是因为1e−4嘛 09/01 10:07:00 - mmengine - INFO - Epoch(train) [1][ 9000/16029] base_lr: 5.044198e-05 lr: 5.044198e-05 eta: 26 days, 17:51:34 time: 0.248321 data_time: 0.002521 memory: 4903 grad_norm: 75.045101 loss: 24.547811 loss_bbox: 2.699222 loss_vis: 0.458490 loss_mle: -0.017420 loss_oks: 20.619778 loss_cls: 0.787740 num_samples: 67.000000 overlaps: 0.486408
我训练自己的模型，mleloss也出现了负值。（我自己的数据集）。我训练的mlecc的loss权重是1，你的是1e-4吗
没有唉 我用的是正常的rtmo-l的config配置
这个应该是正常的吧。rtm0-l的config中MLECCLoss的 loss_weight=1e-2 我个人理解：对于MLECCLoss来说，函数使用了log类型，即loss = -torch.log(prob + 1e-4)， 假设prob的取值范围是[0, 1]，那么此对数函数的取值范围就是[-0.0001, 9.2103]， 所以说，为负值应该是正常的吧。而且 prob = 1.0 for o, t in zip(outputs, targets): prob *= (o * t).sum(dim=-1) 逐元素累加，再乘到prob中，我感觉会超过1，甚至更大，然后对于大数求ln，再取负数，会出现负值吧。 你是如何理解的呢？
dataset_crowdpose = dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='train_coco.json', data_prefix=dict(img='images/'), pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1 )训练数据集别用val_pipeline
看大了BottomupRandomAffine和BottomupResize的区别了。没细读代码，感谢
你好 我在训练RTMO时发现他的loss_mle会训练成负值 为什么会这样是因为1e−4嘛 09/01 10:07:00 - mmengine - INFO - Epoch(train) [1][ 9000/16029] base_lr: 5.044198e-05 lr: 5.044198e-05 eta: 26 days, 17:51:34 time: 0.248321 data_time: 0.002521 memory: 4903 grad_norm: 75.045101 loss: 24.547811 loss_bbox: 2.699222 loss_vis: 0.458490 loss_mle: -0.017420 loss_oks: 20.619778 loss_cls: 0.787740 num_samples: 67.000000 overlaps: 0.486408
我训练自己的模型，mleloss也出现了负值。（我自己的数据集）。我训练的mlecc的loss权重是1，你的是1e-4吗
没有唉 我用的是正常的rtmo-l的config配置
这个应该是正常的吧。rtm0-l的config中MLECCLoss的 loss_weight=1e-2 我个人理解：对于MLECCLoss来说，函数使用了log类型，即loss = -torch.log(prob + 1e-4)， 假设prob的取值范围是[0, 1]，那么此对数函数的取值范围就是[-0.0001, 9.2103]， 所以说，为负值应该是正常的吧。而且 prob = 1.0 for o, t in zip(outputs, targets): prob *= (o * t).sum(dim=-1) 逐元素累加，再乘到prob中，我感觉会超过1，甚至更大，然后对于大数求ln，再取负数，会出现负值吧。 你是如何理解的呢？
确实唉 十分感谢！
@Ben-Louis 最终我的训练，得到的结果如下
而使用rtmo下载的s模型的权重跑的结果如下：
感觉差异还是蛮大的呢，七个点。。所以公开的rtmo-s的训练配置问题参数有问题吗？
请问有试过更大的bs吗？我用的24 效果也很差
dataset_crowdpose = dict( type='HandDataset', data_root=data_root, data_mode=data_mode, ann_file='train_coco.json', data_prefix=dict(img='images/'), pipeline=val_pipeline, # val_pipeline # train_pipeline_stage1 )
Don't use val_pipeline for training datasets
看大了BottomupRandomAffine和BottomupResize的区别了。 没细读代码，感谢
你好 我在训练RTMO时发现他的loss_mle会训练成负值 为什么会这样是因为1e−4嘛 09/01 10:07:00 - mmengine - INFO - Epoch(train) [1][ 9000/16029] base_lr: 5.044198e-05 lr: 5.044198e-05 eta: 26 days, 17:51:34 time: 0.248321 data_time: 0.002521 memory: 4903 grad_norm: 75.045101 loss: 24.547811 loss_bbox: 2.699222 loss_vis: 0.458490 loss_mle: -0.017420 loss_oks: 20.619778 loss_cls: 0.787740 num_samples: 67.000000 overlaps: 0.486408
I trained my own model and mleloss also showed negative values. (my own dataset). The loss weight of the mlecc I trained is 1, and yours is 1e-4
No, alas, I'm using the normal rtmo-l config configuration
This should be normal. loss_weight=1e-2 in the config of rtm0-l, I personally understand: for MLECCLoss, the function uses the log type, that is, loss = -torch.log(prob + 1e-4), assuming that the value range of prob is [0, 1], then the value range of this logarithmic function is [-0.0001, 9.2103], So, A negative value should be normal. And prob = 1.0 for o, t in zip(outputs, targets): prob *= (o * t).sum(dim=-1) add up element by element, and then multiply it into prob, I feel that it will be more than 1, or even greater, and then find ln for large numbers, and then take negative numbers, there will be negative values. How do you understand that?
I still do not understand why the loss function here is negative, Is it not supposed to be always above 0?
