bartmch
bartmch
Ok will do that now, quick side question: have you also looked into grad-cam visualization techniques?
On the first solution ("Set generate_new = False at line 36, visualize.py - This will use the previously saved masks.npy"), I'm getting the following error on line 59 of "explanations.py"...
On the third solution ("Increase the number of masks generated"). I'm still getting totally different heatmaps. I changed from `explainer.generate_masks(N=1000, s=8, p1=0.1, savepath=maskspath)` to `explainer.generate_masks(N=10000, s=8, p1=0.1, savepath=maskspath)` and got...
Hi! Any updates on this?
To build the image for an ARM architecture, in the same repo as the Dockerfile run: `docker build --platform linux/arm64 -t taprosoft/kotaemon:arm64 .`
For those concerned about emulating architectures, you can just create your Dockerfile based on the main repo's Dockerfile. Below Dockerfile creates an ARM-architecture images: ``` #syntax=docker/dockerfile:1.0.0-experimental FROM python:3.10-slim as base_image...
Same issue here, tried all proposed fixes in previous posts, I am still getting 1 cpu core used for each GPU. Within vLLM container I can see all CPU's, these...
What if I use pp>1 would it use #cpu cores > #gpu cores?