# Aligned Xception

**Category:** CNN · **Code:**
[`timm/models/xception_aligned.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/xception_aligned.py)
· **Architectures:** 5 · **Pretrained weights:** 6 (6 with ImageNet-1k results)

Aligned Xception (41, 65, 71 layers) as modified in DeepLab, implemented from scratch and compatible with the TensorFlow
DeepLab weights.

## Papers

* [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357)
* [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1802.02611)

## Usage

See the [Quickstart](../quickstart) for loading pretrained weights, image preprocessing and fine-tuning, and [Feature
Extraction](../feature_extraction) for using the models as backbones.

```py
>>> import timm
>>> model = timm.create_model('xception41p.ra3_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `XceptionAligned` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✓ (strides 2, 4, 8, 16, 32) |
| [`forward_intermediates()`](../model_api#intermediate-features) | ✗ |
| [`prune_intermediate_layers()`](../model_api#intermediate-features) | ✗ |
| [Any input size, no changes needed](../model_api#input-size) | ✓ |
| [`set_input_size()`](../model_api#input-size) | – |
| [`dynamic_img_size=True`](../model_api#input-size) | – |
| [`set_grad_checkpointing()`](../model_api#training-hooks) | ✓ |
| [Layer-wise LR decay (`group_matcher()`)](../model_api#training-hooks) | ✓ |
| [`reset_classifier()`](../model_api#classifier) | ✓ |

✓ supported, ✓ (square) works for square sizes only, ✗ not supported, – not needed (the model already accepts any input
size). Checked by running each feature on a randomly initialized model (`XceptionAligned` with `xception41p` at 299),
other architectures of the same class are expected to behave the same. See the [Model API](../model_api) page for
details.

## Architectures

| Architecture | Params (M) | GMACs | Input size | Pretrained weights |
|---|---:|---:|---:|---:|
| `xception41` | 26.97 | 9.28 | 299 | 1 |
| `xception41p` | 26.91 | 9.25 | 299 | 1 |
| `xception65` | 39.92 | 13.96 | 299 | 2 |
| `xception65p` | 39.82 | 13.91 | 299 | 1 |
| `xception71` | 42.34 | 18.09 | 299 | 1 |

GMACs and parameter counts are for the default input size and classifier of each architecture, from the [benchmark
results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

## Pretrained weights

Top-1 is ImageNet-1k validation accuracy from
[`results-imagenet.csv`](https://github.com/huggingface/pytorch-image-models/blob/main/results/results-imagenet.csv) at
the listed eval size, - if the weight has no ImageNet-1k result (e.g. pretraining or image-text weights). Classes is the
size of the pretrained classifier, none for weights without one.

Weights are grouped by source: the paper or origin given in the pretrained config, else a Hub organization other than
`timm`, else the first part of the pretrained tag (`architecture.tag`). Sources with a single weight are listed under
other.

### `ra3` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `xception41p.ra3_in1k` | 299 | 81.978 | 299 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/xception41p.ra3_in1k) |
| `xception65.ra3_in1k` | 299 | 83.186 | 299 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/xception65.ra3_in1k) |
| `xception65p.ra3_in1k` | 299 | 83.160 | 299 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/xception65p.ra3_in1k) |

### `tf` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `xception41.tf_in1k` | 299 | 78.550 | 299 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/xception41.tf_in1k) |
| `xception65.tf_in1k` | 299 | 79.558 | 299 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/xception65.tf_in1k) |
| `xception71.tf_in1k` | 299 | 79.920 | 299 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/xception71.tf_in1k) |