是否可以在预训练的 tensorflow 模型中删除类别？

Question

I am currently using Tensorflow Object Detection API for my human detection app. I tried filtering in the API itself which worked but I am still not contended by it because it's slow. So I'm wondering if I could remove other categories in the model itself to also make it faster.

If it is not possible, can you please give me other suggestions to make the API faster since I will be using two cameras. Thanks in advance and also pardon my english :)

Answer 1

Your questions addresses several topics for using neural network pretrained models.

Theoretical methods

1. In general, you can always neutralize categories by removing the corresponding neurons in the softmax layer and compute a new softmax layer only with the relevant rows of the matrix.
   This method will surely work (maybe that is what you meant by filtering ) but will not accelerate the network computation time by much, since most of the flops (multiplications and additions) will remain.

2. Similar to decision trees, pruning is possible but may reduce performance. I will explain what pruning means, but note that the accuracy over your categories may remain since you are not just trimming, you are predicting less categories as well.

3. Transfer the learning to your problem. See stanford's course in computer vision here . Most of the times I've seen that works good is by keeping the convolution layers as-is, and preparing a medium-size dataset of the objects you'd like to detect.

I will add more theoretical methods if you request, but the above are the most common and accurate I know.

Practical methods

1. Make sure you are serving your tensorflow model, and not just using an inference python code. This could significantly accelerate performance.

2. You can export the parameters of the network and load them in a faster framework such as CNTK or Caffe . These frameworks work in C++/CSharp and can inference much faster. Make sure you load the weights correctly, some frameworks use different order in tensor dimensions when saving/loading (little/big endian-like issues) .

3. If your application perform inference on several images, you can distribute the computation via several GPUs. **This can also be done in tensorflow, see Using GPUs .

Pruning a neural network

Maybe this is the most interesting method of adapting big networks for simple tasks. You can see a beginner's guide here .

Pruning means that you remove parameters from your network, specifically the whole nodes/neurons in a decision tree/neural network (resp). To do that in object detection, you can do as follows (simplest way):

1. Randomly prune neurons from the fully connected layers.
2. Train one more epoch (or more) with low learning rate, only on objects you'd like to detect.
3. (optional) Perform the above several times for validation and choose best network.

The above procedure is the most basic one, but you can find plenty of papers that suggest algorithms to do so. For example Automated Pruning for Deep Neural Network Compression and An iterative pruning algorithm for feedforward neural networks .

Wish you the best luck with your task!