Problem While training even a small model, I found that the gpu memory occupation neary reached 100%. This seemed odd and it made me to presume that my pytorch training code was not handling gpu memory management properly. Here is a pseudo code for my pytorch training script. With this Read more…
Problem I have trained and saved model checkpoint which was train in GPU 1. However, when I try to load the checkpoint in GPU 0, it fails. The following is my ckpt loading code: this gives me the following error: Solution when loading ckpt data, ensure that device is mapped Read more…
Problem My django project structure looks like this.(only showing files relevant to this problem) As you can see, there are two static dirs that has to be served: ‘prj/app/static/and ‘prj/static. When serving this project from the root of a domain such as ‘localhost:8000’, the following configuration for static files in Read more…
in tensorflow, default initialization used is glorot normal initialization which is also known as xavier normal initialization. To use the same setting in pytorch, the following practice should be done. 2d convolution module example linear module example pytorch supports other initialization functions, and one can use those initialization functions in Read more…
Problem an LSTM module will be used as an example. Assume a simple net that includes an LSTM module. According to the docs, the weight and bias can be accessed by weight_ih_l[k], weight_hh_l[k], bias_ih_l[k], bias_hh_l[k]. For this example, I want to set the b_if to one. So, I could do Read more…
https://github.com/pytorch/pytorch/issues/20102 also mentioned in tensorflow docs: https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTM
here is a simple code to convert dir/file of images to png in batch. for installing imagemagick, use this command: