ShuffleNet VS. MobileNet: idea and code
ShuffleNet V1
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices(arXiv)
Core Idea: Channel Shuffle
Channel shuffle with two stacked group convolutions. GConv stands for group convolution. a) two stacked convolution layers with the same number of groups. Each output channel only relates to the input channels wi...
PyTorch Image Segmentation: Deeplab ASPP Module, Non-local Nets
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
arXiv
Atrous Spatial Pyramid Pooling (ASPP) Module
To classify the center pixel (orange), ASPP exploits multi-scale features by employing multiple parallel filters with different rates. The effective Field-Of-Views are shown in di...
Metric of Image Segmentation: Mean IOU(in Numpy)
Mean IOU
Intersection-Over-Union (IoU)
IoU is the area of overlap between the predicted segmentation and the ground truth divided by the area of union between the predicted segmentation and the ground truth.
For binary (two classes) or multi-class segmentation, the mean IoU of the image is calculated by taking the IoU of each class and avera...
CVPR 2020: Object Detection(2)
Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
Author: Qi Fan, Wei Zhuo, Yu-Wing Tai
Arxiv: 1908.01998
GitHub
Problem
Few-shot object detection: aims to detect objects of unseen class with a few training examples.
Insight
Central to our method is the Attention-RPN and the multi-relation module which fully exp...
CVPR 2020: Object Detection(1)
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection(Oral)
Author: Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, Stan Z. Li
Arxiv: 1912.02424
GitHub
Problem
Anchor-based VS. Anchor-Free detectors, what’s the true difference
Insight
We first point out that the essential differenc...
CVPR 2020: Self-Supervised Learning
Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics(Oral)
Author: Simon Jenni, Hailin Jin, Paolo Favaro
Arxiv: 2004.02331
Problem
Recognizing the pose of objects from a single image that for learning uses only unlabelled videos and a weak empirical prior on the object poses.
Insight
Prevent appearance leakage in Cyc...
Fix "The following signatures couldn't be verified because the public key is not available" for nvidia-docker
Error: Nvidia-docker’s signatures couldn’t be verified
W: An error occurred during the signature verification. The repository is not updated and the previous index files will be used. GPG error: https://nvidia.github.io/libnvidia-container/ubuntu18.04/amd64 InRelease: The following signatures couldn't be verified because the public key is not ...
Print Error Info without Stopping Training
In the flowling ways, the error is prompt without distrupt training process.
for i in range(conf.max_iters + 1):
# Train a single iteration on the current data instance
try:
model.train_one_iter(i, input_images)
except KeyboardInterrupt:
raise
except Exception as e:
print('Something went wrong in iterati...
130 post articles, 17 pages.