A pretrained model, as my encoder, has several layers 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)
)
)
.
.
.
.
.
.
I need to extract features of specific layers of the above mentioned model and I am using hook method as follows:
import torch.nn as nn
class my_class(nn.Module):
def __init__(self, pretrained=False):
super(my_class, self).__init__()
self.featureExtractor =TimeSformer(img_size=224, num_classes=400, num_frames=8, attention_type='divided_space_time',
pretrained_model='/home/TimeSformer_divST_16x16_448_K400.pyth')
self.featureExtractor=nn.DataParallel(self.featureExtractor)
self.list = list(self.featureExtractor.children())
self.activation = {}
def get_activation(name):
def hook(model, input, output):
self.activation[name] = output.detach()
return hook
self.featureExtractor.model.blocks[4].register_forward_hook(get_activation('block4'))
self.featureExtractor.model.blocks[8].register_forward_hook(get_activation('block8'))
self.featureExtractor.model.blocks[4].temporal_attn.register_forward_hook(get_activation('block4.temporal_attn'))
self.featureExtractor.model.blocks[11].register_forward_hook(get_activation('block11'))
def forward(self, x, out_consp = False):
b = self.featureExtractor(x)
block4_output_Temporal_att = self.activation['block4.temporal_attn']
block4_output = self.activation['block4']
block8_output = self.activation['block8']
block11_output = self.activation['block11']
.
.
.
.
The problem is I face the following error:
File “/home/TimeSformer/models/timesformer.py”, line 30, in init self.featureExtractor.model.blocks[4].register_forward_hook(get_activation(‘block4’))
File “/home/miniconda3/envs/pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py”, line 1185, in getattr raise AttributeError(“‘{}’ object has no attribute ‘{}’”.format( AttributeError: ‘DataParallel’ object has no attribute ‘model’
How can I solve the problem