I got a runtime error at evaluation phase of my simple siamese network as RuntimeError: cuda runtime error (2) : out of memory at the line of executing forward pass. Some comments on stackoverflow suggests to define x and y with volatile=T…

See spyder's issue. For my case, installing PyOpenGL fixed the error as conda install pyopengl

See this tutorial. Set requires_grad=True for all tensors we compute gradients w.r.t. them. [code lang='python'] input and output x = torch.randn(N, D_in, device=device, dtype=dtype) y = torch.randn(N, D_out, device=device, dtype=dtype) pa…

See the tutorial. It's quite simple (Keras provides simpler interface though). A neural network is defined as a class that has a forward function. The forward function defines how input data is processed through the network. PyTorch automa…

Super easy installation GUI on the web as below

Inspired by this stackoverflow answer and keras.callbacks.CSVLogger, I implemented a callback function to save loss on each batch. [code lang='python'] class LossHistory(Callback): def __init__(self, filename, separator=',', append=False):…

If Leap Motion SDK installation failed with dpkg command, the site gives you the answer. Before running sudo dpkg --install Leap-*-x64.deb, we should first make a file /lib/systemd/system/leapd.service with the following contents. Otherwis…