# dla-34¶

## Use Case and High-Level Description¶

The dla-34 model is one of the DLA models designed to perform image classification. This model was pre-trained in PyTorch*. All DLA (Deep Layer Aggregation) classification models have been pre-trained on the ImageNet dataset. For details about this family of models, check out the Code for the CVPR Paper “Deep Layer Aggregation”.

Metric

Value

Type

Classification

GFLOPs

6.1368

MParams

15.7344

Source framework

PyTorch*

Metric

Original model

Converted model

Top 1

74.64%

74.64%

Top 5

92.06%

92.06%

## Input¶

### Original model¶

Image, name - data, shape - 1, 3, 224, 224, format is B, C, H, W, where:

• B - batch size

• C - channel

• H - height

• W - width

Channel order is RGB. Mean values - [123.675, 116.28, 103.53], scale values - [58.395, 57.12, 57.375].

### Converted model¶

Image, name - data, shape - 1, 3, 224, 224, format is B, C, H, W, where:

• B - batch size

• C - channel

• H - height

• W - width

Channel order is BGR

## Output¶

### Original model¶

Object classifier according to ImageNet classes, name - prob, shape - 1, 1000, output data format is B, C, where:

• B - batch size

• C - predicted probabilities for each class in [0, 1] range

### Converted model¶

Object classifier according to ImageNet classes, name - prob, shape - 1, 1000, output data format is B, C, where:

• B - batch size

• C - predicted probabilities for each class in [0, 1] range

python3 <omz_dir>/tools/downloader/downloader.py --name <model_name>
python3 <omz_dir>/tools/downloader/converter.py --name <model_name>