Closed Kev1n3zz closed 1 year ago
作者你好,感谢你精彩的工作。 我在读论文的时候尝试寻找MCA和MPCA指标的相关信息
请问MCA就是代码benchmark中注释部分展示的群体行为识别准确率吗? 请问想要得到接近论文的准确率超参数应该如何设置? 另外MPCA指标应该从什么地方找到指标介绍呢?
另外是否可以讲解一下
#Params
参数量计算的方法?
Hi, Thanks for your interest in our work!
#Params
, I use fvcore package:
from fvcore.nn import activation_count, flop_count, parameter_count, parameter_count_table
非常感谢您的回复
请问对论文中Dynamic Walk
和代码中Dynamic_Person_Inference
是否有较详细的参考资料呢?
只通过公开发表在ICCV2021上的论文我还是不太能看懂代码T_T
非常感谢您的回复 请问对论文中
Dynamic Walk
和代码中Dynamic_Person_Inference
是否有较详细的参考资料呢? 只通过公开发表在ICCV2021上的论文我还是不太能看懂代码T_T
Hi, I think a good reference is Deformable Convolutional Networks.
感谢回复,我也注意到了DCN这篇文章。 再次感谢您的这篇有意思的论文.
请问在考虑代码的时候是否有考虑过针对视频的bbox引入deformable_roi_pooling
呢?
请问在考虑代码的时候是否有考虑过针对视频的bbox引入
deformable_roi_pooling
呢?
I think it is worth trying, and you could design Dynamic Pooling (it should follow the design of Dynamic Inference Network). However, for a fair comparison, you may need to perform controlled experiments to demonstrate its efficacy compared to average pooling.
你好,请问可以请教一下在计算FLOPs的时候 flop_count
方法用在什么地方了吗?
E:\code\DIN\infer_module\dynamic_infer_module.py:315: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
k2, T, N = offset.shape[3] // 2, offset.shape[1], offset.shape[2] # 9,10,12
Unsupported operator aten::softmax encountered 1 time(s)
Unsupported operator aten::meshgrid encountered 2 time(s)
Unsupported operator aten::mul encountered 15 time(s)
Unsupported operator aten::add encountered 22 time(s)
Unsupported operator aten::sub encountered 14 time(s)
Unsupported operator aten::abs encountered 8 time(s)
Unsupported operator aten::rsub encountered 8 time(s)
Unsupported operator aten::sum encountered 2 time(s)
Unsupported operator aten::mean encountered 1 time(s)
FLOPs: 11397120.0
我在DPI方法前加入不能得到正确的结果。
我在DPI方法前加入不能得到正确的结果。
@Kev1n3zz Try codes below:
if __name__=='__main__':
DPI = Dynamic_Person_Inference(
in_dim = 128,
person_mat_shape = (10,12),
stride = 1,
kernel_size = [3, 3],
dynamic_sampling = True,
sampling_ratio = [1],
group = 1,
scale_factor = True,
beta_factor = False,)
person_features = torch.randn((1, 10, 12, 128))
macs, params = profile(DPI, inputs = (person_features, ))
MAC2FLOP(macs, params, module_name = 'DPI')
感谢回复,请问我在CAD下仅使用res18就获得了96.x%以上的1阶段准确率(完全按照您的代码),请问CAD是否还适合作为GAR任务的通用评估数据集吗?另外如您在另外一个问题里的回复,模型在CAD数据集上存在严重过拟合,这让我认为在CAD上是否取得良好的表现是随机而没有道理的。
感谢回复,请问我在CAD下仅使用res18就获得了96.x%以上的1阶段准确率(完全按照您的代码),请问CAD是否还适合作为GAR任务的通用评估数据集吗?另外如您在另外一个问题里的回复,模型在CAD数据集上存在严重过拟合,这让我认为在CAD上是否取得良好的表现是随机而没有道理的。
I agree with you. CAD is insufficient to serve as a good benchmark for GAR currently as the model capacity grows larger and larger. Thus, I give three suggestions: i) run multiple times to get a series of results in that you can calculate the mean and standard deviation of your method; ii) make your pytorch code deterministic; iii) use other benchmarks, like Volleyball and the newly-proposed NBA dataset.
感谢回复,谢谢。
作者你好,感谢你精彩的工作。 我在读论文的时候尝试寻找MCA和MPCA指标的相关信息
请问MCA就是代码benchmark中注释部分展示的群体行为识别准确率吗? 请问想要得到接近论文的准确率超参数应该如何设置? 另外MPCA指标应该从什么地方找到指标介绍呢?
另外是否可以讲解一下
#Params
参数量计算的方法?