Feeds
提问
How to do activation quantization of EACH LAYER in lgraph or dlnetwork?
for activation of each layer in dlnetwork or lgraph, how to do quantization? My dlnetwork is just a piece of network, not a who...
2 years 前 | 1 个回答 | 1
1
个回答提问
How to convert data from floating point to fixed point? Not function, only data.
I want to convert an array of single precision data into fixed point and I have proposed length of the data I want. How to conv...
2 years 前 | 1 个回答 | 0
1
个回答提问
How to add breakpoints when I am pausing a running code
I add breakpoint in the debugging mode when pausing a running code. But it's grey. It gets ignored. Continue running the code w...
3 years 前 | 1 个回答 | 0
1
个回答提问
mnrfit takes too long
It takes more than two weeks for a single run of mnrfit. It just reaches 43/100 iter/iterLim in 'nominalFit' after 1.5 weeks. ...
3 years 前 | 1 个回答 | 0
1
个回答提问
minibatchqueue or arrayDatastore drops my data precision from double to single
I get XTrain from MNIST by processImagesMNIST and put it on GPU, so its type is gpuArray dlarray. then I use these code to make...
3 years 前 | 1 个回答 | 0
1
个回答提问
Do matlab has build-in mnist dataset for CNN training? If I load it as dlarray, how do I train it with CNN?
This documentation shows the example to design CNN for digit image classification. Is the 'toolbox/nnet/nndemos/nndatasets/Digi...
3 years 前 | 1 个回答 | 0
1
个回答提问
What's fid in "Training a Model from Scratch"?
For this DL example, What's the 'fid' in the first code block? rawImgDataTrain = uint8 (fread(fid, numImg * numRows * numCols,...
3 years 前 | 2 个回答 | 0
2
个回答提问
processImagesMNIST doesn't give the right data format for trainNetwork
Loading mnist: According to the dataset for DL, I load MNIST by this: filenameImagesTrain = 'train-images-idx3-ubyte.gz'; f...
3 years 前 | 1 个回答 | 0
