- [Description of Random Situation](#description-of-random-situation)
- [ModelZoo Homepage](#modelzoo-homepage)
# [InceptionV4 Description](#contents)
Inception-v4 is a convolutional neural network architecture that builds on previous iterations of the Inception family by simplifying the architecture and using more inception modules than Inception-v3. This idea was proposed in the paper Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, published in 2016.
[Paper](https://arxiv.org/pdf/1602.07261.pdf) Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi. Computer Vision and Pattern Recognition[J]. 2016.
# [Model architecture](#contents)
The overall network architecture of InceptionV4 is show below:
[Link](https://arxiv.org/pdf/1602.07261.pdf)
# [Dataset](#contents)
Dataset used can refer to paper.
- Dataset size: 125G, 1250k colorful images in 1000 classes
- Train: 120G, 1200k images
- Test: 5G, 50k images
- Data format: RGB images.
- Note: Data will be processed in src/dataset.py
# [Features](#contents)
## [Mixed Precision(Ascend)](#contents)
The [mixed precision](https://www.mindspore.cn/tutorial/training/en/master/advanced_use/enable_mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data formats, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware.
For FP16 operators, if the input data type is FP32, the backend of MindSpore will automatically handle it with reduced precision. Users could check the reduced-precision operators by enabling INFO log and then searching ‘reduce precision’.
'keep_checkpoint_max' # max numbers to keep checkpoints
'save_checkpoint_epochs' # save checkpoints per n epoch
'lr_init' # init leaning rate
'lr_end' # end of learning rate
'lr_max' # max bound of learning rate
'warmup_epochs' # warmup epoch numbers
'start_epoch' # number of start epoch range[1, epoch_size]
```
## [Training process](#contents)
### Usage
You can start training using python or shell scripts. The usage of shell scripts as follows:
- Ascend:
```bash
# distribute training example(8p)
sh scripts/run_distribute_train_ascend.sh RANK_TABLE_FILE DATA_PATH DATA_DIR
# standalone training
sh scripts/run_standalone_train_ascend.sh DEVICE_ID DATA_DIR
```
> Notes:
> RANK_TABLE_FILE can refer to [Link](https://www.mindspore.cn/tutorial/training/en/master/advanced_use/distributed_training_ascend.html) , and the device_ip can be got as [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools). For large models like InceptionV4, it's better to export an external environment variable`export HCCL_CONNECT_TIMEOUT=600`to extend hccl connection checking time from the default 120 seconds to 600 seconds. Otherwise, the connection could be timeout since compiling time increases with the growth of model size.
>
> This is processor cores binding operation regarding the `device_num` and total processor numbers. If you are not expect to do it, remove the operations `taskset` in `scripts/run_distribute_train.sh`
Training result will be stored in the example path. Checkpoints will be stored at `ckpt_path` by default, and training log will be redirected to `./log.txt` like following.
