Add first ConvNext-XXLarge CLIP -> IN-1k fine-tune and IN-12k intermediate fine-tunes for convnext-base/large CLIP models. modeltop1top5img_sizeparam_countgmacsmacts convnext_xxlarge.clip_laion2b_soup_ft_in1k 88.612 98.704 256 846.47 198.09 124.45 convnext_large_mlp.clip_laion2b_soup_...
Update convnext_xxlarge default LayerNorm eps to 1e-5 (for CLIP weights, improved stability) 0.8.15dev0 Feb 20, 2023 Add 320x320 convnext_large_mlp.clip_laion2b_ft_320 and convnext_lage_mlp.clip_laion2b_ft_soup_320 CLIP image tower weights for features & fine-tune 0.8.13dev0 pyp...
Add first ConvNext-XXLarge CLIP -> IN-1k fine-tune and IN-12k intermediate fine-tunes for convnext-base/large CLIP models. modeltop1top5img_sizeparam_countgmacsmacts convnext_xxlarge.clip_laion2b_soup_ft_in1k 88.612 98.704 256 846.47 198.09 124.45 convnext_large_mlp.clip_laion2b_soup_...
Update convnext_xxlarge default LayerNorm eps to 1e-5 (for CLIP weights, improved stability) 0.8.15dev0 Feb 20, 2023 Add 320x320 convnext_large_mlp.clip_laion2b_ft_320 and convnext_lage_mlp.clip_laion2b_ft_soup_320 CLIP image tower weights for features & fine-tune 0.8.13dev0 pyp...
Add first ConvNext-XXLarge CLIP -> IN-1k fine-tune and IN-12k intermediate fine-tunes for convnext-base/large CLIP models. modeltop1top5img_sizeparam_countgmacsmacts convnext_xxlarge.clip_laion2b_soup_ft_in1k 88.612 98.704 256 846.47 198.09 124.45 convnext_large_mlp.clip_laion2b_soup_...
Update convnext_xxlarge default LayerNorm eps to 1e-5 (for CLIP weights, improved stability) 0.8.15dev0 Feb 20, 2023 Add 320x320 convnext_large_mlp.clip_laion2b_ft_320 and convnext_lage_mlp.clip_laion2b_ft_soup_320 CLIP image tower weights for features & fine-tune 0.8.13dev0 pyp...
Update convnext_xxlarge default LayerNorm eps to 1e-5 (for CLIP weights, improved stability) 0.8.15dev0 Feb 20, 2023 Add 320x320 convnext_large_mlp.clip_laion2b_ft_320 and convnext_lage_mlp.clip_laion2b_ft_soup_320 CLIP image tower weights for features & fine-tune 0.8.13dev0 pyp...
Add first ConvNext-XXLarge CLIP -> IN-1k fine-tune and IN-12k intermediate fine-tunes for convnext-base/large CLIP models. modeltop1top5img_sizeparam_countgmacsmacts convnext_xxlarge.clip_laion2b_soup_ft_in1k 88.612 98.704 256 846.47 198.09 124.45 convnext_large_mlp.clip_laion2b_soup_...
Add quickgelu ViT variants for OpenAI, DFN, MetaCLIP weights that use it (less efficient) Improved typing added to ResNet, MobileNet-v3 thanks to Aryan ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 releaseOct
Add quickgelu ViT variants for OpenAI, DFN, MetaCLIP weights that use it (less efficient) Improved typing added to ResNet, MobileNet-v3 thanks to Aryan ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 releaseOct