mossishahi

Multiple input

5

Whats the solution if we have multiple paired fastq files which we want to run fastp on them. suppose 120 files named like (s_1_1_qseq.fq to s_1_120_qseq.fq) and their pairs are...

function definition is not allowed here

4

Hi I have searched many issues over your github telling the same story, still, I was wondering to know if there is any update or solution for my problem: ```...

Using SupContrast loss for non-image application

1

Hey I am about to use the [SupConLoss](https://github.com/HobbitLong/SupContrast/blob/331aab5921c1def3395918c05b214320bef54815/losses.py#L11) for my specific application: As I am embedding some graphs and would like to make the embeddings of similar graphs to get...

**IMPORTANT: Please search among the [Pull requests](../pulls) before creating one.** ## Description ## How has this been tested? ## Closes

Missed requirements

1

I have followed the installation requirements of segger but the following line reveals a few dependencies missed: `from segger.prediction.predict_parquet import segment, load_model ` and I could get this issue sorted...

Spatialdata and dask Comatibility

1

hi segger dev team, i guess you can also confirm that the community which uses Segger is also a user of Spatialdata. I've been facing a requirement incompatibility between segger...

Error during the prediction of segmentation

5

I was running `segment` method as follows in my script: ``` from segger.training.segger_data_module import SeggerDataModule # from segger.prediction.predict import predict, load_model from segger.models.segger_model import Segger from segger.training.train import LitSegger from...

KeyError in DataLoader when (tx, belongs, bd).edge_label is missing for some samples

2

I’m running into a `KeyError` in the PyTorch Geometric `DataLoader` when using the package. Some `.pt `files in my dataset do not include an `edge_label` in the (tx, belongs, bd)...

Low speed with 5k genes

5

Unfortunately, the training speed is lower than expected in the case we have ~5k genes. In my case, it tooks almost 1.5h per hour.