# TNT

**Category:** ViT · **Code:**
[`timm/models/tnt.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/tnt.py) ·
**Architectures:** 3 · **Pretrained weights:** 3 (3 with ImageNet-1k results)

Transformer in Transformer (TNT) models the structure inside each patch with an inner transformer over sub-patches,
alongside the outer transformer over patches.

## Papers

* [Transformer in Transformer](https://arxiv.org/abs/2103.00112)

## 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('tnt_s_patch16_224.in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `TNT` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✓ (strides 16, 16, 16) |
| [`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 (`TNT` with `tnt_s_legacy_patch16_224` at 224),
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 |
|---|---:|---:|---:|---:|
| `tnt_b_patch16_224` | 65.43 | 14.10 | 224 | 1 |
| `tnt_s_legacy_patch16_224` | 23.76 | 5.24 | 224 | 1 |
| `tnt_s_patch16_224` | 23.77 | 5.25 | 224 | 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.

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `tnt_b_patch16_224.in1k` | 224 | 82.864 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/tnt_b_patch16_224.in1k) |
| `tnt_s_legacy_patch16_224.in1k` | 224 | 81.512 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/tnt_s_legacy_patch16_224.in1k) |
| `tnt_s_patch16_224.in1k` | 224 | 81.506 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/tnt_s_patch16_224.in1k) |