-
I'm using getorganelle to extract mitochondrial genomes from insects. I first do an assembly using SPAdes (because we use that output for other downstream tasks anyway), and then I run get_organelle_f…
-
[tiny11.log](https://github.com/user-attachments/files/16739690/tiny11.log)
The error occurred during the system streamlining, as shown in the log code below.
Deployment Image Servicing and Manageme…
-
This task is related to reducing the size of our Stage1 outputs to a level where they can be easily stored on disk along with our CAF files.
Currently, our Stage1 file sizes are running at ~300 MB/e…
-
This was brought to my attention by @chergert and it is easily reproduced in current c10s Workstation for e…
-
# Summary
Replace redis with solidcache
# Why?
Slimming down our prod
# Details
Check that everything we use redis for will still works. Make it so!
# Criteria for completion
- [ ] through check of wh…
cielf updated
2 weeks ago
-
Dear @liuzhuang13,
I guess we should prune some channel of subsequent conv layer' kernels after pruning current layer. Am I right?
So I can not figure out how to slim residual block using your m…
-
Hi @liuzhuang13,
Thank you for a great work. I saw that you leveraged scaling factors of Batch normalization to prune incoming and outgoing weights at conv layers, However in DenseNet after a basic…
-
Hi, Have you ever try it with MobileNet?
-
Currently the Helm chart provides more cluster wide permissions against the k8s api-server than may be needed, depending on configuration of dask-gateway.
The following PRs are opened related to th…
-
Hi, thank you for your work. My model is resnet20. If I want to use your slimming algorithm, just modify this parameter --depth to 20? Is there anything else that needs to be modified?