Sunyuan
Sunyuan
Meet this interesting work so late. Here is my little doubt. https://github.com/zhoubolei/CAM/blob/c63f2850a7a3dadc21fa1b021875e2d4d053ece5/pytorch_CAM.py#L48 1. The dimension of `weight_softmax[idx]` should be 512. However, for `layer4`'s `nc`, it should be 256. Is there...
1. CodeBase1: I need to use the weighted random sampler for ImageNet1000, so, i checke this issue. [link](https://github.com/NVIDIA/DALI/issues/1356#issuecomment-570390878). Then, I followed this [link](https://docs.nvidia.com/deeplearning/dali/user-guide/docs/examples/frameworks/pytorch/pytorch-external_input.html) to get my own codes, including `Sampler`,...
Does the parameter seem to be useless? According to Doc. num_attempts (int, optional, default = 10) – Maximum number of attempts used to choose random area and aspect ratio. what...
Interesting idea. However, the $\gamma$ and $\beta$ of the background are processed on the standard normal distribution feature, but the parameters of foreground are processed on the style shifted distribution...
It seems that the prototype augmentation is very similar to semantic augmentation. Are there any specific differences in details? Implicit semantic data augmentation for deep networks. NIPS.
I found in ur table 7 or original icarl paper. 10 task. Cifar100-B0. 32-layer ResNet. I cannot achieve the results about 64.04. Or give some insights?
我在配置mmdetection3d的时候： ```command cd ~ git clone https://github.com/open-mmlab/mmdetection3d.git cd mmdetection3d git checkout v0.17.1 # Other versions may not be compatible. python setup.py install pip install -r requirements.txt # Install packages for...
Could you pls explain the insights behind adding early stop training? Why we need to stop the gradient of attention networks? https://github.com/yhlleo/uaggan/blob/1a7ced40022169865a5fb237681ef8138fe3e747/models/uag_gan_model.py#L215
Nice work. The loss results for the test set are reported in Figure 5, but what about the accuracy. In my experimental results, although the loss does drop, it seems...
Amazing work. sorry to interrupt you. However, for the underlined part of formula 5, it is difficult for me to understand that it is related to the feature distance. Could...