VIT

• Based on vit from blip code base

• https://github.com/salesforce/BLIP

Classes

class models.coda_prompt_utils.vit.Attention(dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0.0, proj_drop=0.0)

Bases: Module

forward(x, prompt=None)

get_attention_map()

get_attn_gradients()

save_attention_map(attention_map)

save_attn_gradients(attn_gradients)

class models.coda_prompt_utils.vit.Block(dim, num_heads, mlp_ratio=4.0, qkv_bias=False, qk_scale=None, drop=0.0, attn_drop=0.0, drop_path=0.0, act_layer=<class 'torch.nn.modules.activation.GELU'>, norm_layer=<class 'torch.nn.modules.normalization.LayerNorm'>)

Bases: Module

forward(x, prompt=None)

class models.coda_prompt_utils.vit.VisionTransformer(qk_scale=None, args=None, **kwargs)

Bases: VisionTransformer

forward(x, prompt=None, q=None, train=False, task_id=None)