prakashjay
prakashjay
Thanks for your response. One more question: 1) When assigning anchor boxes, shall we compute max_iou over each pyramid level ? or do we need to compute all the anchor...
Thanks man for your time. I using RetinaNet. Regards, Prakash V On Mon, Mar 5, 2018 at 8:00 PM, Cheng Yang wrote: > It depends what Network you choose. For...
Yup everything is working now as desired . Will be releasing the blog post soon. Thanks for ur response man. Really helped me :) On Mar 7, 2018 7:02 AM,...
use Group norm instead of batch norm . it is more stable.
As of now I doing this ```python from diffusers.models.attention_processor import AttnProcessor for blocks in model.down_blocks: if hasattr(blocks, "attentions"): for attn in blocks.attentions: attn.processor = AttnProcessor() for blocks in model.up_blocks: if...
my current approach is here https://github.com/prakashjayy/genai/blob/main/flow/02_mean_flow.ipynb