ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 release Oct 20, 2023 SigLIP image tower weights supported in vision_transformer.py. Great potential for fine-tune and downstream feature use. Experimental 'register' support in vit models as per Vision Transformers Need Reg...
ViTTextLargePatch14 123.1M 6.67G [None, 77] vit_text_large_patch14_clip.h5 Encoder 34.16M 559.6G [None, 512, 512, 3] encoder_v1_5.h5 UNet 859.5M 404.4G [None, 64, 64, 4] unet_v1_5.h5 Decoder 49.49M 1259.5G [None, 64, 64, 4] decoder_v1_5.h5Segmentation...
PASSL包含 SimCLR,MoCo v1/v2,BYOL,CLIP,PixPro,simsiam, SwAV, BEiT,MAE 等图像自监督算法以及 Vision Transformer,DEiT,Swin Transformer,CvT,T2T-ViT,MLP-Mixer,XCiT,ConvNeXt,PVTv2 等基础视觉算法 - PaddlePaddle/PASSL
ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 release Oct 20, 2023 SigLIP image tower weights supported in vision_transformer.py. Great potential for fine-tune and downstream feature use. Experimental 'register' support in vit models as per Vision Transformers Need Reg...
ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 release Oct 20, 2023 SigLIP image tower weights supported in vision_transformer.py. Great potential for fine-tune and downstream feature use. Experimental 'register' support in vit models as per Vision Transformers Need Reg...
ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 release Oct 20, 2023 SigLIP image tower weights supported in vision_transformer.py. Great potential for fine-tune and downstream feature use. Experimental 'register' support in vit models as per Vision Transformers Need Reg...
ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 release Oct 20, 2023 SigLIP image tower weights supported in vision_transformer.py. Great potential for fine-tune and downstream feature use. Experimental 'register' support in vit models as per Vision Transformers Need Reg...
ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 release Oct 20, 2023 SigLIP image tower weights supported in vision_transformer.py. Great potential for fine-tune and downstream feature use. Experimental 'register' support in vit models as per Vision Transformers Need...
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
ImageNet-12k fine-tuned (from LAION-2B CLIP) convnext_xxlarge 0.9.9 release Oct 20, 2023 SigLIP image tower weights supported in vision_transformer.py. Great potential for fine-tune and downstream feature use. Experimental 'register' support in vit models as per Vision Transformers Need Reg...