I want to extract the features from certain blocks of the TimeSformer model and also want to remove the last two layers.
import torch from timesformer.models.vit import TimeSformer model = TimeSformer(img_size=224, num_classes=400, num_frames=8, attention_type='divided_space_time', pretrained_model='/path/to/pretrained/model.pyth')
The print of the model is as follows:
TimeSformer(
(model): VisionTransformer(
(dropout): Dropout(p=0.0, inplace=False)
(patch_embed): PatchEmbed(
(proj): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))
)
(pos_drop): Dropout(p=0.0, inplace=False)
(time_drop): Dropout(p=0.0, inplace=False)
(blocks): ModuleList( #************
(0): Block(
(norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
(attn_drop): Dropout(p=0.0, inplace=False)
)
(temporal_norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(temporal_attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
(attn_drop): Dropout(p=0.0, inplace=False)
)
(temporal_fc): Linear(in_features=768, out_features=768, bias=True)
(drop_path): Identity()
(norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=768, out_features=3072, bias=True)
(act): GELU()
(fc2): Linear(in_features=3072, out_features=768, bias=True)
(drop): Dropout(p=0.0, inplace=False)
)
)
(1): Block(
(norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
(attn_drop): Dropout(p=0.0, inplace=False)
)
(temporal_norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(temporal_attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
(attn_drop): Dropout(p=0.0, inplace=False)
)
(temporal_fc): Linear(in_features=768, out_features=768, bias=True)
(drop_path): DropPath()
(norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=768, out_features=3072, bias=True)
(act): GELU()
(fc2): Linear(in_features=3072, out_features=768, bias=True)
(drop): Dropout(p=0.0, inplace=False)
)
)
.
.
.
.
.
.
(11): Block(
(norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
(attn_drop): Dropout(p=0.0, inplace=False)
)
(temporal_norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(temporal_attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
(attn_drop): Dropout(p=0.0, inplace=False)
)
(temporal_fc): Linear(in_features=768, out_features=768, bias=True)
(drop_path): DropPath()
(norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=768, out_features=3072, bias=True)
(act): GELU()
(fc2): Linear(in_features=3072, out_features=768, bias=True)
(drop): Dropout(p=0.0, inplace=False)
)
)
)
(norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) **** I want to remove this layer*****
(head): Linear(in_features=768, out_features=400, bias=True) **** I want to remove this layer*****
)
)
Specifically, I want to extract the outputs of the 4th, 8th and 11th blocks of the model and removing the lats two layers. How can I do this. I tried using TimeSformer.blocks[0] but that was not working.
Update :
I have a Class and I need to access the aforementioned blocks of the TimeSformer as the output of this class. The input of this class is a 5D tensor. This is the non-modified code that I use for extracting the outputs of the aforementioned blocks:
class Model(nn.Module):
def __init__(self, pretrained=False):
super(Model, self).__init__()
self.model =TimeSformer(img_size=224, num_classes=400, num_frames=8, attention_type='divided_space_time',
pretrained_model='/home/user/models/TimeSformer_divST_16x16_448_K400.pyth')
self.activation = {}
def get_activation(name):
def hook(model, input, output):
self.activation[name] = output.detach()
return hook
self.model.model.blocks[4].register_forward_hook(get_activation('block4'))
self.model.model.blocks[8].register_forward_hook(get_activation('block8'))
self.model.model.blocks[11].register_forward_hook(get_activation('block11'))
block4_output = self.activation['block4']
block8_output = self.activation['block8']
block11_output = self.activation['block11']
def forward(self, x, out_consp = False):
features2, features3, features4 = self.model(x)
Advertisement
Answer
To extract the intermediate output from specific layers, you can register it as a hook, the example is showed by the snipcode below:
import torch
from timesformer.models.vit import TimeSformer
model = TimeSformer(img_size=224, num_classes=400, num_frames=8, attention_type='divided_space_time', pretrained_model='/path/to/pretrained/model.pyth')
activation = {}
def get_activation(name):
def hook(model, input, output):
activation[name] = output.detach()
return hook
model.model.blocks[4].register_forward_hook(get_activation('block4'))
model.model.blocks[8].register_forward_hook(get_activation('block8'))
model.model.blocks[11].register_forward_hook(get_activation('block11'))
x = torch.randn(3,3,224,224)
output = model(x)
block4_output = activation['block4']
block8_output = activation['block8']
block11_output = activation['block11']
To remove the last two layers, you can replace them with Identity:
model.norm = torch.nn.Identity() model.head= torch.nn.Identity()