from model.backbone.CPVT import CPVTV2 import torch from torch import nn if __name__ == '__main__': input=torch.randn(1,3,224,224) model = CPVTV2( patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4], qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1]) output=model(input) print(output.shape)