Rohit Pawar
@hirwa-nshuti, sorry for late response, Could you merge following PR?
> Resolve the merge conflicts for CI check and merging Should I pull and merge conflicts and then push the code ? @hirwa-nshuti Is this way you saying ?
_, feat_bev_e, seg_bev_e, center_bev_e, offset_bev_e = model( rgb_camXs=rgb_camXs, pix_T_cams=pix_T_cams, cam0_T_camXs=cam0_T_camXs, vox_util=vox_util, rad_occ_mem0=None) If we consider above as as mentioned model, then rgb_camXs:[-0.5, 0.5] range values with shape (6,3,448,800) (N,C,H,W). pix_T_cams...
Also adding, my recent visualisation seems to be below attaches photo with ground truth. Above training graph is same i.e. unstable or say its not training.  
@aharley Sir, I successfully completed the fine-tuning on Carla GT and addressed two key engineering aspects during the process: a) Ground Truth Collection Extracted semantic maps from Carla. Main challenge:...
Hello @TParcollet and @Adel-Moumen , I am Rohit. I would love to contribute in this issue if this is a incomplete work yet to build SpeechLLM fine-tunning. As i worked...