DeepMicrobes

DeepMicrobes copied to clipboard

Error occurred during model training.

13

Hello, I didn't encounter any errors when training small amounts of data, but when I tried to train several Gs worth of data, I received the following error. Could you...

XLOXL

Hello. I noticed that the repository does not provide a pretrained model. I was wondering if it is possible to provide a pretrained model so that I can use DeepMicrobes...

LoadStar822

关于DeepMicrobe论文中的细节问题想向您请教

2

您好我对您的研究非常感兴趣，希望能够复现您的结果用于研究。 但是在复现的过程中遇到了一些问题，非常希望能够得到您的帮助！以下是我总结的问题： 1. 文中句子：The number of reads to simulate depended on how many training steps were required for models to conver. 想问下您的训练集在使用ART进行模拟时，最终模拟的read数是多少（覆盖度参数-f是几×），方便提供一下模拟训练数据的命令吗。 2. Evaluation sets验证集的覆盖度参数-f是几×呢，方便提供一下模拟验证集的命令吗？ 3. 生成训练集过程中，您在Assign过label以后，是将所有的.fa文件拼接在一起做后续的simulation，trim等操作后得到train.tfrec吗？ 4. 由于训练集和验证集数量都很大，想问下您使用的什么方法或者工具来快速剔除掉验证集中和训练集重复的pair-end数据。 感谢您花时间阅读我的消息，期望得到您的回复。

htaohan

Training on multiple genomes

5

Hello, I have my own dataset of about ~1500 references that I want to train the genus model on. I have simulated reads for them individually and now at the...

Gayathri142

Something about "subset*.tfrec"

7

Hello! I think your work is great. I'd love to try running your code, but after following your steps this happens, can you tell me how I can fix it?...

yongrenr

About train_epoch

2

Hello, I would like to ask if the setting of train_epoch has an impact on the model. I see that you have set the default value to 1, but the...

XLOXL

The use of Benchmark Dataset

2

Hello, When using the pretrained model and evaluating it with the Benchmark Dataset, which is composed of 10k simulated paired-end reads per MAG, do we need to fine-tune the model...

JiayiJennie

Issues with vocabulary file

1

I have some issues with converting fastq files for prediction. Even though I have downloaded the kmers.txt and exported the paths, it says: Traceback (most recent call last): File "/home/xxx/DeepMicrobes/scripts/seq2tfrec_kmer.py",...

isilayc

预测过程中GPU使用的问题

1

您好我对您的研究非常感兴趣，我想知道DeepMicrobes的预测运行时间。 当我设置 export CUDA_VISIBLE_DEVICES=0 # GPU 0 predict_DeepMicrobes.sh -i 4000.tfrec -m /home/gyc/DeepMicrobes/weights -o 4000_result 进行预测时，发现机器的GPU显存没有发生变化，即他是使用CPU进行预测的。 代码有设置默认GPU吗？

yongrenr

Hi, Is there a way to access the pre-trained weights. Also, how to retrieve the embeddings of the input sequences?

BrinthaVP