QiZuo
QiZuo
train_fea_dir: "/data/features/best_features/paris" # path of the features for training SVD. I find this in oxford.yaml, and it is strange that when I run main/index.py, the shell post a error: `[LoadFeature]:...
[V1_mbv3_h36m,mpiinf,coco,mpii,lsp,muco,crowdpose_g0,1,2,3.log](https://github.com/Arthur151/ROMP/files/8338065/V1_mbv3_h36m.mpiinf.coco.mpii.lsp.muco.crowdpose_g0.1.2.3.log) 可以帮忙看一下这个mobilenetv3的训练日志吗？ 他的validation 指标下降到140&90附近就感觉卡住了，而且我把30epoch的模型拿出来测试了一下，发现SMPL body会飘在人物上面，我的想法是训练的时候body center heatmap应该是最先收敛的，所以即便pose上误差比较大，det loss应该收敛，也就是不会产生这种飘在人物上方的现象，不知道您训练的时候有没有这种问题，希望您能给出建议～ 我在resnet的基础上将batch_size 调整为了128，lr 相应x2 为 0.0001 图示：
现在512x512的大概cpu需要100ms，我想尝试一下降低分辨率，想请教下作者有没有类似的尝试？
Maybe the difference between CPU...I only get 50ms/frame on my computer. I intend to use cuda to accelerate it and use it for some further usage. Can you give me...
As shown in paper, the generator is equaled to a simple linear kernel, then why we still need to use 'imresize' func to resize the picture, can we save all...
`class DiceLoss(nn.Module): def __init__(self): super().__init__() self.epsilon = 1e-5` def forward(self, output, target): # print(output.shape) # print(target.shape) assert output.size() == target.size(), "'input' and 'target' must have the same shape" # 在classes上做softmax...
Hi, can you help me with translating the format in IDR's .npz file into the transformation.json file. Actually, I do not understand the relationship between these two formats.
I capture some pictures using my phone, but when i finish the colmap mapper process. it send out this message. I find code related to it. ` pts_arr = []...
sorry it is l1 indeed.....