Skip to content

Deep Layer Aggregation

Extending “shallow” skip connections, Dense Layer Aggregation (DLA) incorporates more depth and sharing. The authors introduce two structures for deep layer aggregation (DLA): iterative deep aggregation (IDA) and hierarchical deep aggregation (HDA). These structures are expressed through an architectural framework, independent of the choice of backbone, for compatibility with current and future networks.

IDA focuses on fusing resolutions and scales while HDA focuses on merging features from all modules and channels. IDA follows the base hierarchy to refine resolution and aggregate scale stage-bystage. HDA assembles its own hierarchy of tree-structured connections that cross and merge stages to aggregate different levels of representation.

How do I use this model on an image?

To load a pretrained model:

import timm
model = timm.create_model('dla102', pretrained=True)

To load and preprocess the image:

import urllib
from PIL import Image
from import resolve_data_config
from import create_transform

config = resolve_data_config({}, model=model)
transform = create_transform(**config)

url, filename = ("", "dog.jpg")
urllib.request.urlretrieve(url, filename)
img ='RGB')
tensor = transform(img).unsqueeze(0) # transform and add batch dimension

To get the model predictions:

import torch
with torch.no_grad():
    out = model(tensor)
probabilities = torch.nn.functional.softmax(out[0], dim=0)
# prints: torch.Size([1000])

To get the top-5 predictions class names:

# Get imagenet class mappings
url, filename = ("", "imagenet_classes.txt")
urllib.request.urlretrieve(url, filename) 
with open("imagenet_classes.txt", "r") as f:
    categories = [s.strip() for s in f.readlines()]

# Print top categories per image
top5_prob, top5_catid = torch.topk(probabilities, 5)
for i in range(top5_prob.size(0)):
    print(categories[top5_catid[i]], top5_prob[i].item())
# prints class names and probabilities like:
# [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]

Replace the model name with the variant you want to use, e.g. dla102. You can find the IDs in the model summaries at the top of this page.

To extract image features with this model, follow the timm feature extraction examples, just change the name of the model you want to use.

How do I finetune this model?

You can finetune any of the pre-trained models just by changing the classifier (the last layer).

model = timm.create_model('dla102', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
To finetune on your own dataset, you have to write a training loop or adapt timm's training script to use your dataset.

How do I train this model?

You can follow the timm recipe scripts for training a new model afresh.


      title={Deep Layer Aggregation}, 
      author={Fisher Yu and Dequan Wang and Evan Shelhamer and Trevor Darrell},