# PP-LCNetV2

**Category:** Efficient/Mobile · **Code:**
[`timm/models/lcnetv2.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/lcnetv2.py) ·
**Architectures:** 3 · **Pretrained weights:** 4 (0 with ImageNet-1k results)

PP-LCNetV2 from PaddleClas is a CPU oriented network built on PP-LCNet. The depthwise convolutions of the later stages
are re-parameterizable multi-scale branches, and SE and shortcuts are used sparingly to avoid latency penalties on CPU.

## Papers

* [Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve
  Backbones](https://arxiv.org/abs/2103.05959)

## 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('lcnetv2_base.paddle_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `LCNetV2` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✓ (strides 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 (`LCNetV2` with `lcnetv2_small` 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 |
|---|---:|---:|---:|---:|
| `lcnetv2_base` | 6.69 | - | 224 | 2 |
| `lcnetv2_large` | 10.54 | - | 224 | 1 |
| `lcnetv2_small` | 4.13 | - | 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 |
|---|---:|---:|---:|---:|---|---|
| `lcnetv2_base.paddle_in1k` | 224 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/lcnetv2_base.paddle_in1k) |
| `lcnetv2_base.ssld_in1k` | 224 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/lcnetv2_base.ssld_in1k) |
| `lcnetv2_large.paddle_in1k` | 224 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/lcnetv2_large.paddle_in1k) |
| `lcnetv2_small.paddle_in1k` | 224 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/lcnetv2_small.paddle_in1k) |