Chunwei Ma

use ``` D_real = D_real.mean().unsqueeze(0) ```

We may go to /usr/share/pixmaps/FBReader/ to manually substitute the icons with meaningful ones?

Hi, If you only want to predict RT values for a handful of testing data (without training), I would suggest using: ``` python prediction_emb_cpu.py max_rt param_cpu/dia_all_epo20_dim24_conv12/dia_all_epo20_dim24_conv12_filled.pt 12 data/DeepRTtest.txt ``` where...

Hi, sorry for the delayed response. Yes, generally all the RT values here are in minutes so "max_rt = 11.2 min", and "time_scale = 60" converts RT in the data...

Hi! For the calibration from a pretrained model (run1) to another LC run (run2), please: 1. Select a certain ratio of peptides from run2 as the calibration peptides (better with...

The method is **transfer learning**. The model is first **pre-trained** on data1 from LC run1, then **fine-tuned** on data2 from LC run2. The only difference between using/not using this pretraining...

I guess you're using pytorch version >= 1.0 which was released after this package was developed. According to [this issue](https://github.com/NVIDIA/flownet2-pytorch/issues/113) could you try to change from ``` meter_loss.add(state['loss'].data[0]) ``` to...

I have tried pytorch version 1.1.0 and it works well without error. Are you using CPU or GPU and what's your pytorch and cuda version? You may check pytorch version...

Good suggestion. The output retention time of DeepRT is determined by the training data one uses, and here is [one dataset](https://github.com/horsepurve/DeepRTplus/blob/master/data/dia.txt) from the [paper](https://www.nature.com/articles/sdata201431) which is normalized by the iRT...

Could you try changing config.py from ``` dict_path = '' max_length = 50 ``` to ``` dict_path = 'data/mod.txt' max_length = 66 ``` because 66 is the max length in...