Depth (d) : Scaling network depth is the most common way used by many ConvN. The intuition is that deeper ConvNet can capture richer and more complex features, and generalize well on new tasks . However, deeper networks are also more difficult to train due to the vanishing gradient problem ...
feature pyramid network Lin, Tsung-Yi, et al. Feature pyramid networks for object detection. Proceedings of the IEEE conference on computer vision and pattern recognition . 2017. (FPN) Chao, Hanqing, et al. Gaitset: Regarding gait as a set for cross-view ga ...
Deep learning is like a black box. Its learning process takes the inputs and the desired outputs, and then updates its internal states, so that the calculated outputs get as close as possible from the desired output. So machine learning sometimes is called model fitting. Decompose the learning pro ...
when running at the code of self.criterion(outputs, labels), where I use CrossEntropy as my loss function, I meet the bug of D imension out of range (expected to be in range of , but got 1) Solution: From the doc of CrossEntropy ( https://pytorch.org/docs/stable/nn.html?highlight=cros ...