forked from mindspore-Ecosystem/mindspore
fix spelling bug
This commit is contained in:
zlq2020
parent
d92605db01
commit
3e75eb5180
|
|
@ -20,7 +20,6 @@
|
|||
|
||||
# [MobileNetV2 Description](#contents)
|
||||
|
||||
|
||||
MobileNetV2 is tuned to mobile phone CPUs through a combination of hardware- aware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances.Nov 20, 2019.
|
||||
|
||||
[Paper](https://arxiv.org/pdf/1905.02244) Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for MobileNetV2." In Proceedings of the IEEE International Conference on Computer Vision, pp. 1314-1324. 2019.
|
||||
|
|
@ -38,11 +37,10 @@ The overall network architecture of MobileNetV2 is show below:
|
|||
Dataset used: [imagenet](http://www.image-net.org/)
|
||||
|
||||
- Dataset size: ~125G, 1.2W colorful images in 1000 classes
|
||||
- Train: 120G, 1.2W images
|
||||
- Test: 5G, 50000 images
|
||||
- Train: 120G, 1.2W images
|
||||
- Test: 5G, 50000 images
|
||||
- Data format: RGB images.
|
||||
- Note: Data will be processed in src/dataset.py
|
||||
|
||||
- Note: Data will be processed in src/dataset.py
|
||||
|
||||
# [Features](#contents)
|
||||
|
||||
|
|
@ -54,14 +52,13 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
|
|||
# [Environment Requirements](#contents)
|
||||
|
||||
- Hardware:Ascend
|
||||
- Prepare hardware environment with Ascend. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
|
||||
- Prepare hardware environment with Ascend. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
|
||||
- Framework
|
||||
- [MindSpore](https://www.mindspore.cn/install/en)
|
||||
- For more information, please check the resources below
|
||||
- [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html)
|
||||
- [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html)
|
||||
|
||||
|
||||
# [Script description](#contents)
|
||||
|
||||
## [Script and sample code](#contents)
|
||||
|
|
@ -84,7 +81,6 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
|
|||
├── export.py # export checkpoint files into air/onnx
|
||||
```
|
||||
|
||||
|
||||
## [Script Parameters](#contents)
|
||||
|
||||
Parameters for both training and evaluation can be set in config.py
|
||||
|
|
@ -113,13 +109,11 @@ Parameters for both training and evaluation can be set in config.py
|
|||
|
||||
### Usage
|
||||
|
||||
|
||||
You can start training using python or shell scripts. The usage of shell scripts as follows:
|
||||
|
||||
- bash run_train.sh [Ascend] [RANK_TABLE_FILE] [DATASET_PATH] [PRETRAINED_CKPT_PATH]\(optional)
|
||||
- bash run_train.sh [GPU] [DEVICE_ID_LIST] [DATASET_PATH] [PRETRAINED_CKPT_PATH]\(optional)
|
||||
|
||||
|
||||
### Launch
|
||||
|
||||
``` bash
|
||||
|
|
@ -133,7 +127,7 @@ You can start training using python or shell scripts. The usage of shell scripts
|
|||
Training result will be stored in the example path. Checkpoints trained by `Ascend` will be stored at `./train/device$i/checkpoint` by default, and training log will be redirected to `./train/device$i/train.log`. Checkpoints trained by `GPU` will be stored in `./train/checkpointckpt_$i` by default, and training log will be redirected to `./train/train.log`.
|
||||
`train.log` is as follows:
|
||||
|
||||
```
|
||||
``` bash
|
||||
epoch: [ 0/200], step:[ 624/ 625], loss:[5.258/5.258], time:[140412.236], lr:[0.100]
|
||||
epoch time: 140522.500, per step time: 224.836, avg loss: 5.258
|
||||
epoch: [ 1/200], step:[ 624/ 625], loss:[3.917/3.917], time:[138221.250], lr:[0.200]
|
||||
|
|
@ -150,7 +144,7 @@ You can start training using python or shell scripts. The usage of shell scripts
|
|||
|
||||
### Launch
|
||||
|
||||
```
|
||||
``` bash
|
||||
# infer example
|
||||
shell:
|
||||
Ascend: sh run_infer_quant.sh Ascend ~/imagenet/val/ ~/train/mobilenet-60_1601.ckpt
|
||||
|
|
@ -160,9 +154,9 @@ You can start training using python or shell scripts. The usage of shell scripts
|
|||
|
||||
### Result
|
||||
|
||||
Inference result will be stored in the example path, you can find result like the followings in `./val/infer.log`.
|
||||
Inference result will be stored in the example path, you can find result like the following in `./val/infer.log`.
|
||||
|
||||
```
|
||||
``` bash
|
||||
result: {'acc': 0.71976314102564111}
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ def parse_args():
|
|||
>>> parse_args()
|
||||
"""
|
||||
parser = ArgumentParser(description="mindspore distributed training launch "
|
||||
"helper utilty that will spawn up "
|
||||
"helper utility that will spawn up "
|
||||
"multiple distributed processes")
|
||||
parser.add_argument("--nproc_per_node", type=int, default=1,
|
||||
help="The number of processes to launch on each node, "
|
||||
|
|
|
|||
|
|
@ -37,19 +37,18 @@ The overall network architecture of Resnet50 is show below:
|
|||
Dataset used: [ImageNet2012](http://www.image-net.org/)
|
||||
|
||||
- Dataset size 224*224 colorful images in 1000 classes
|
||||
- Train：1,281,167 images
|
||||
- Test： 50,000 images
|
||||
- Train：1,281,167 images
|
||||
- Test： 50,000 images
|
||||
- Data format：jpeg
|
||||
- Note：Data will be processed in dataset.py
|
||||
- Note：Data will be processed in dataset.py
|
||||
- Download the dataset, the directory structure is as follows:
|
||||
|
||||
```
|
||||
```python
|
||||
└─dataset
|
||||
├─ilsvrc # train dataset
|
||||
└─validation_preprocess # evaluate dataset
|
||||
```
|
||||
|
||||
|
||||
# [Features](#contents)
|
||||
|
||||
## [Mixed Precision](#contents)
|
||||
|
|
@ -60,14 +59,13 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
|
|||
# [Environment Requirements](#contents)
|
||||
|
||||
- Hardware:Ascend
|
||||
- Prepare hardware environment with Ascend. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
|
||||
- Prepare hardware environment with Ascend. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
|
||||
- Framework
|
||||
- [MindSpore](https://www.mindspore.cn/install/en)
|
||||
- For more information, please check the resources below：
|
||||
- [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html)
|
||||
- [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html)
|
||||
|
||||
|
||||
# [Script description](#contents)
|
||||
|
||||
## [Script and sample code](#contents)
|
||||
|
|
@ -124,18 +122,19 @@ Parameters for both training and evaluation can be set in config.py
|
|||
### Usage
|
||||
|
||||
- Ascend: sh run_train.sh Ascend [RANK_TABLE_FILE] [DATASET_PATH] [PRETRAINED_CKPT_PATH]\(optional)
|
||||
|
||||
### Launch
|
||||
|
||||
```
|
||||
```bash
|
||||
# training example
|
||||
Ascend: bash run_train.sh Ascend ~/hccl.json ~/imagenet/train/ ~/pretrained_ckeckpoint
|
||||
```
|
||||
|
||||
### Result
|
||||
|
||||
Training result will be stored in the example path. Checkpoints will be stored at `./train/device$i/` by default, and training log will be redirected to `./train/device$i/train.log` like followings.
|
||||
Training result will be stored in the example path. Checkpoints will be stored at `./train/device$i/` by default, and training log will be redirected to `./train/device$i/train.log` like following.
|
||||
|
||||
```
|
||||
```bash
|
||||
epoch: 1 step: 5004, loss is 4.8995576
|
||||
epoch: 2 step: 5004, loss is 3.9235563
|
||||
epoch: 3 step: 5004, loss is 3.833077
|
||||
|
|
@ -153,7 +152,7 @@ You can start training using python or shell scripts. The usage of shell scripts
|
|||
|
||||
### Launch
|
||||
|
||||
```
|
||||
```bash
|
||||
# infer example
|
||||
shell:
|
||||
Ascend: sh run_infer.sh Ascend ~/imagenet/val/ ~/train/Resnet50-30_5004.ckpt
|
||||
|
|
@ -163,9 +162,9 @@ You can start training using python or shell scripts. The usage of shell scripts
|
|||
|
||||
### Result
|
||||
|
||||
Inference result will be stored in the example path, you can find result like the followings in `./eval/infer.log`.
|
||||
Inference result will be stored in the example path, you can find result like the following in `./eval/infer.log`.
|
||||
|
||||
```
|
||||
```bash
|
||||
result: {'acc': 0.76576314102564111}
|
||||
```
|
||||
|
||||
|
|
@ -191,7 +190,7 @@ result: {'acc': 0.76576314102564111}
|
|||
| Total time | 8pcs: 17 hours(30 epochs with pretrained) |
|
||||
| Parameters (M) | 25.5 |
|
||||
| Checkpoint for Fine tuning | 197M (.ckpt file) |
|
||||
| Scripts | [resnet50-quant script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet50_quant) |
|
||||
| Scripts | [resnet50-quant script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet50_quant) |
|
||||
|
||||
### Inference Performance
|
||||
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ def parse_args():
|
|||
>>> parse_args()
|
||||
"""
|
||||
parser = ArgumentParser(description="mindspore distributed training launch "
|
||||
"helper utilty that will spawn up "
|
||||
"helper utility that will spawn up "
|
||||
"multiple distributed processes")
|
||||
parser.add_argument("--nproc_per_node", type=int, default=1,
|
||||
help="The number of processes to launch on each node, "
|
||||
|
|
|
|||
|
|
@ -93,7 +93,7 @@ class DetectionEngine:
|
|||
|
||||
def _nms(self, dets, thresh):
|
||||
"""Calculate NMS."""
|
||||
# conver xywh -> xmin ymin xmax ymax
|
||||
# convert xywh -> xmin ymin xmax ymax
|
||||
x1 = dets[:, 0]
|
||||
y1 = dets[:, 1]
|
||||
x2 = x1 + dets[:, 2]
|
||||
|
|
@ -185,7 +185,7 @@ class DetectionEngine:
|
|||
|
||||
x_top_left = x - w / 2.
|
||||
y_top_left = y - h / 2.
|
||||
# creat all False
|
||||
# create all False
|
||||
flag = np.random.random(cls_emb.shape) > sys.maxsize
|
||||
for i in range(flag.shape[0]):
|
||||
c = cls_argmax[i]
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ cp ../*.py ./eval$3
|
|||
cp -r ../src ./eval$3
|
||||
cd ./eval$3 || exit
|
||||
env > env.log
|
||||
echo "start infering for device $DEVICE_ID"
|
||||
echo "start inferring for device $DEVICE_ID"
|
||||
python eval.py \
|
||||
--data_dir=$DATASET_PATH \
|
||||
--pretrained=$CHECKPOINT_PATH \
|
||||
|
|
|
|||
|
|
@ -94,7 +94,7 @@ def get_interp_method(interp, sizes=()):
|
|||
Neighbors method. (used by default).
|
||||
4: Lanczos interpolation over 8x8 pixel neighborhood.
|
||||
9: Cubic for enlarge, area for shrink, bilinear for others
|
||||
10: Random select from interpolation method metioned above.
|
||||
10: Random select from interpolation method mentioned above.
|
||||
Note:
|
||||
When shrinking an image, it will generally look best with AREA-based
|
||||
interpolation, whereas, when enlarging an image, it will generally look best
|
||||
|
|
|
|||
|
|
@ -58,7 +58,7 @@ class YoloBlock(nn.Cell):
|
|||
|
||||
Args:
|
||||
in_channels: Integer. Input channel.
|
||||
out_chls: Interger. Middle channel.
|
||||
out_chls: Integer. Middle channel.
|
||||
out_channels: Integer. Output channel.
|
||||
|
||||
Returns:
|
||||
|
|
@ -108,7 +108,7 @@ class YOLOv3(nn.Cell):
|
|||
Args:
|
||||
backbone_shape: List. Darknet output channels shape.
|
||||
backbone: Cell. Backbone Network.
|
||||
out_channel: Interger. Output channel.
|
||||
out_channel: Integer. Output channel.
|
||||
|
||||
Returns:
|
||||
Tensor, output tensor.
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ def has_valid_annotation(anno):
|
|||
# if all boxes have close to zero area, there is no annotation
|
||||
if _has_only_empty_bbox(anno):
|
||||
return False
|
||||
# keypoints task have a slight different critera for considering
|
||||
# keypoints task have a slight different criteria for considering
|
||||
# if an annotation is valid
|
||||
if "keypoints" not in anno[0]:
|
||||
return True
|
||||
|
|
|
|||
|
|
@ -121,7 +121,7 @@ def parse_args():
|
|||
args.rank = get_rank()
|
||||
args.group_size = get_group_size()
|
||||
|
||||
# select for master rank save ckpt or all rank save, compatiable for model parallel
|
||||
# select for master rank save ckpt or all rank save, compatible for model parallel
|
||||
args.rank_save_ckpt_flag = 0
|
||||
if args.is_save_on_master:
|
||||
if args.rank == 0:
|
||||
|
|
@ -140,6 +140,14 @@ def conver_training_shape(args):
|
|||
training_shape = [int(args.training_shape), int(args.training_shape)]
|
||||
return training_shape
|
||||
|
||||
def build_quant_network(network):
|
||||
quantizer = QuantizationAwareTraining(bn_fold=True,
|
||||
per_channel=[True, False],
|
||||
symmetric=[True, False],
|
||||
one_conv_fold=False)
|
||||
network = quantizer.quantize(network)
|
||||
return network
|
||||
|
||||
|
||||
def train():
|
||||
"""Train function."""
|
||||
|
|
@ -168,11 +176,7 @@ def train():
|
|||
config = ConfigYOLOV3DarkNet53()
|
||||
# convert fusion network to quantization aware network
|
||||
if config.quantization_aware:
|
||||
quantizer = QuantizationAwareTraining(bn_fold=True,
|
||||
per_channel=[True, False],
|
||||
symmetric=[True, False],
|
||||
one_conv_fold=False)
|
||||
network = quantizer.quantize(network)
|
||||
network = build_quant_network(network)
|
||||
|
||||
network = YoloWithLossCell(network)
|
||||
args.logger.info('finish get network')
|
||||
|
|
@ -198,11 +202,8 @@ def train():
|
|||
|
||||
lr = get_lr(args)
|
||||
|
||||
opt = Momentum(params=get_param_groups(network),
|
||||
learning_rate=Tensor(lr),
|
||||
momentum=args.momentum,
|
||||
weight_decay=args.weight_decay,
|
||||
loss_scale=args.loss_scale)
|
||||
opt = Momentum(params=get_param_groups(network), learning_rate=Tensor(lr), momentum=args.momentum,
|
||||
weight_decay=args.weight_decay, loss_scale=args.loss_scale)
|
||||
|
||||
network = TrainingWrapper(network, opt)
|
||||
network.set_train()
|
||||
|
|
@ -213,9 +214,7 @@ def train():
|
|||
ckpt_config = CheckpointConfig(save_checkpoint_steps=args.ckpt_interval,
|
||||
keep_checkpoint_max=ckpt_max_num)
|
||||
save_ckpt_path = os.path.join(args.outputs_dir, 'ckpt_' + str(args.rank) + '/')
|
||||
ckpt_cb = ModelCheckpoint(config=ckpt_config,
|
||||
directory=save_ckpt_path,
|
||||
prefix='{}'.format(args.rank))
|
||||
ckpt_cb = ModelCheckpoint(config=ckpt_config, directory=save_ckpt_path, prefix='{}'.format(args.rank))
|
||||
cb_params = _InternalCallbackParam()
|
||||
cb_params.train_network = network
|
||||
cb_params.epoch_num = ckpt_max_num
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
- [Model Architecture](#model-architecture)
|
||||
- [Dataset](#dataset)
|
||||
- [Environment Requirements](#environment-requirements)
|
||||
- [Quick Start](#quick-start)
|
||||
- [Quick Start](#quick-start)
|
||||
- [Script Description](#script-description)
|
||||
- [Script and Sample Code](#script-and-sample-code)
|
||||
- [Script Parameters](#script-parameters)
|
||||
|
|
@ -19,7 +19,6 @@
|
|||
- [Description of Random Situation](#description-of-random-situation)
|
||||
- [ModelZoo Homepage](#modelzoo-homepage)
|
||||
|
||||
|
||||
# [YOLOv3_ResNet18 Description](#contents)
|
||||
|
||||
YOLOv3 network based on ResNet-18, with support for training and evaluation.
|
||||
|
|
@ -30,24 +29,25 @@ YOLOv3 network based on ResNet-18, with support for training and evaluation.
|
|||
|
||||
The overall network architecture of YOLOv3 is show below:
|
||||
|
||||
And we use ResNet18 as the backbone of YOLOv3_ResNet18. The architecture of ResNet18 has 4 stages. The ResNet architecture performs the initial convolution and max-pooling using 7×7 and 3×3 kernel sizes respectively. Afterward, every stage of the network has different Residual blocks (2, 2, 2, 2) containing two 3×3 conv layers. Finally, the network has an Average Pooling layer followed by a fully connected layer.
|
||||
|
||||
And we use ResNet18 as the backbone of YOLOv3_ResNet18. The architecture of ResNet18 has 4 stages. The ResNet architecture performs the initial convolution and max-pooling using 7×7 and 3×3 kernel sizes respectively. Afterward, every stage of the network has different Residual blocks (2, 2, 2, 2) containing two 3×3 conv layers. Finally, the network has an Average Pooling layer followed by a fully connected layer.
|
||||
|
||||
# [Dataset](#contents)
|
||||
|
||||
Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
|
||||
|
||||
Dataset used: [COCO2017](<http://images.cocodataset.org/>)
|
||||
Dataset used: [COCO2017](<http://images.cocodataset.org/>)
|
||||
|
||||
- Dataset size：19G
|
||||
- Train：18G，118000 images
|
||||
- Val：1G，5000 images
|
||||
- Annotations：241M，instances，captions，person_keypoints etc
|
||||
- Train：18G，118000 images
|
||||
- Val：1G，5000 images
|
||||
- Annotations：241M，instances，captions，person_keypoints etc
|
||||
- Data format：image and json files
|
||||
- Note：Data will be processed in dataset.py
|
||||
|
||||
- Dataset
|
||||
|
||||
1. The directory structure is as follows:
|
||||
|
||||
```
|
||||
.
|
||||
├── annotations # annotation jsons
|
||||
|
|
@ -55,7 +55,7 @@ Dataset used: [COCO2017](<http://images.cocodataset.org/>)
|
|||
└── val2017 # infer dataset
|
||||
```
|
||||
|
||||
2. Organize the dataset infomation into a TXT file, each row in the file is as follows:
|
||||
2. Organize the dataset information into a TXT file, each row in the file is as follows:
|
||||
|
||||
```
|
||||
train2017/0000001.jpg 0,259,401,459,7 35,28,324,201,2 0,30,59,80,2
|
||||
|
|
@ -63,63 +63,61 @@ Dataset used: [COCO2017](<http://images.cocodataset.org/>)
|
|||
|
||||
Each row is an image annotation which split by space, the first column is a relative path of image, the others are box and class infomations of the format [xmin,ymin,xmax,ymax,class]. `dataset.py` is the parsing script, we read image from an image path joined by the `image_dir`(dataset directory) and the relative path in `anno_path`(the TXT file path), `image_dir` and `anno_path` are external inputs.
|
||||
|
||||
|
||||
# [Environment Requirements](#contents)
|
||||
|
||||
- Hardware（Ascend）
|
||||
- Prepare hardware environment with Ascend processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
|
||||
- Prepare hardware environment with Ascend processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
|
||||
- Framework
|
||||
- [MindSpore](https://www.mindspore.cn/install/en)
|
||||
- For more information, please check the resources below：
|
||||
- [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html)
|
||||
- [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html)
|
||||
|
||||
|
||||
|
||||
# [Quick Start](#contents)
|
||||
|
||||
After installing MindSpore via the official website, you can start training and evaluation on Ascend as follows:
|
||||
After installing MindSpore via the official website, you can start training and evaluation on Ascend as follows:
|
||||
|
||||
- runing on Ascend
|
||||
- running on Ascend
|
||||
|
||||
```shell script
|
||||
#run standalone training example
|
||||
sh run_standalone_train.sh [DEVICE_ID] [EPOCH_SIZE] [MINDRECORD_DIR] [IMAGE_DIR] [ANNO_PATH]
|
||||
|
||||
|
||||
#run distributed training example
|
||||
sh run_distribute_train.sh [DEVICE_NUM] [EPOCH_SIZE] [MINDRECORD_DIR] [IMAGE_DIR] [ANNO_PATH] [RANK_TABLE_FILE]
|
||||
|
||||
|
||||
#run evaluation example
|
||||
sh run_eval.sh [DEVICE_ID] [CKPT_PATH] [MINDRECORD_DIR] [IMAGE_DIR] [ANNO_PATH]
|
||||
```
|
||||
|
||||
# [Script Description](#contents)
|
||||
|
||||
## [Script and Sample Code](#contents)
|
||||
|
||||
```
|
||||
```python
|
||||
└── cv
|
||||
├── README.md // descriptions about all the models
|
||||
├── mindspore_hub_conf.md // config for mindspore hub
|
||||
└── yolov3_resnet18
|
||||
└── yolov3_resnet18
|
||||
├── README.md // descriptions about yolov3_resnet18
|
||||
├── scripts
|
||||
├── scripts
|
||||
├── run_distribute_train.sh // shell script for distributed on Ascend
|
||||
├── run_standalone_train.sh // shell script for distributed on Ascend
|
||||
└── run_eval.sh // shell script for evaluation on Ascend
|
||||
├── src
|
||||
├── src
|
||||
├── dataset.py // creating dataset
|
||||
├── yolov3.py // yolov3 architecture
|
||||
├── config.py // parameter configuration
|
||||
├── config.py // parameter configuration
|
||||
└── utils.py // util function
|
||||
├── train.py // training script
|
||||
├── train.py // training script
|
||||
└── eval.py // evaluation script
|
||||
```
|
||||
|
||||
## [Script Parameters](#contents)
|
||||
|
||||
```
|
||||
Major parameters in train.py and config.py as follows:
|
||||
|
||||
```python
|
||||
device_num: Use device nums, default is 1.
|
||||
lr: Learning rate, default is 0.001.
|
||||
epoch_size: Epoch size, default is 50.
|
||||
|
|
@ -133,24 +131,23 @@ After installing MindSpore via the official website, you can start training and
|
|||
img_shape: Image height and width used as input to the model.
|
||||
```
|
||||
|
||||
|
||||
## [Training Process](#contents)
|
||||
|
||||
### Training on Ascend
|
||||
|
||||
To train the model, run `train.py` with the dataset `image_dir`, `anno_path` and `mindrecord_dir`. If the `mindrecord_dir` is empty, it wil generate [mindrecord](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/convert_dataset.html) file by `image_dir` and `anno_path`(the absolute image path is joined by the `image_dir` and the relative path in `anno_path`). **Note if `mindrecord_dir` isn't empty, it will use `mindrecord_dir` rather than `image_dir` and `anno_path`.**
|
||||
|
||||
- Stand alone mode
|
||||
|
||||
```
|
||||
```bash
|
||||
sh run_standalone_train.sh 0 50 ./Mindrecord_train ./dataset ./dataset/train.txt
|
||||
```
|
||||
|
||||
The input variables are device id, epoch size, mindrecord directory path, dataset directory path and train TXT file path.
|
||||
|
||||
|
||||
- Distributed mode
|
||||
|
||||
```
|
||||
```bash
|
||||
sh run_distribute_train.sh 8 150 /data/Mindrecord_train /data /data/train.txt /data/hccl.json
|
||||
```
|
||||
|
||||
|
|
@ -158,7 +155,7 @@ To train the model, run `train.py` with the dataset `image_dir`, `anno_path` and
|
|||
|
||||
You will get the loss value and time of each step as following:
|
||||
|
||||
```
|
||||
```bash
|
||||
epoch: 145 step: 156, loss is 12.202981
|
||||
epoch time: 25599.22742843628, per step time: 164.0976117207454
|
||||
epoch: 146 step: 156, loss is 16.91706
|
||||
|
|
@ -168,19 +165,20 @@ You will get the loss value and time of each step as following:
|
|||
epoch: 148 step: 156, loss is 10.431475
|
||||
epoch time: 23634.241580963135, per step time: 151.50154859591754
|
||||
epoch: 149 step: 156, loss is 14.665991
|
||||
epoch time: 24118.8325881958, per step time: 154.60790120638333
|
||||
epoch time: 24118.8325881958, per step time: 154.60790120638333
|
||||
epoch: 150 step: 156, loss is 10.779521
|
||||
epoch time: 25319.57221031189, per step time: 162.30495006610187
|
||||
```
|
||||
|
||||
Note the results is two-classification(person and face) used our own annotations with coco2017, you can change `num_classes` in `config.py` to train your dataset. And we will suport 80 classifications in coco2017 the near future.
|
||||
Note the results is two-classification(person and face) used our own annotations with coco2017, you can change `num_classes` in `config.py` to train your dataset. And we will support 80 classifications in coco2017 the near future.
|
||||
|
||||
## [Evaluation Process](#contents)
|
||||
|
||||
### Evaluation on Ascend
|
||||
|
||||
To eval, run `eval.py` with the dataset `image_dir`, `anno_path`(eval txt), `mindrecord_dir` and `ckpt_path`. `ckpt_path` is the path of [checkpoint](https://www.mindspore.cn/tutorial/training/en/master/use/save_model.html) file.
|
||||
|
||||
```
|
||||
```bash
|
||||
sh run_eval.sh 0 yolo.ckpt ./Mindrecord_eval ./dataset ./dataset/eval.txt
|
||||
```
|
||||
|
||||
|
|
@ -188,18 +186,18 @@ The input variables are device id, checkpoint path, mindrecord directory path, d
|
|||
|
||||
You will get the precision and recall value of each class:
|
||||
|
||||
```
|
||||
```bash
|
||||
class 0 precision is 88.18%, recall is 66.00%
|
||||
class 1 precision is 85.34%, recall is 79.13%
|
||||
```
|
||||
|
||||
Note the precision and recall values are results of two-classification(person and face) used our own annotations with coco2017.
|
||||
|
||||
|
||||
# [Model Description](#contents)
|
||||
|
||||
## [Performance](#contents)
|
||||
|
||||
### Evaluation Performance
|
||||
### Evaluation Performance
|
||||
|
||||
| Parameters | Ascend |
|
||||
| -------------------------- | ----------------------------------------------------------- |
|
||||
|
|
@ -217,7 +215,6 @@ Note the precision and recall values are results of two-classification(person an
|
|||
| Parameters (M) | 189 |
|
||||
| Scripts | [yolov3_resnet18 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_resnet18) | [yolov3_resnet18 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_resnet18) |
|
||||
|
||||
|
||||
### Inference Performance
|
||||
|
||||
| Parameters | Ascend |
|
||||
|
|
@ -233,9 +230,9 @@ Note the precision and recall values are results of two-classification(person an
|
|||
|
||||
# [Description of Random Situation](#contents)
|
||||
|
||||
In dataset.py, we set the seed inside “create_dataset" function. We also use random seed in train.py.
|
||||
In dataset.py, we set the seed inside “create_dataset" function. We also use random seed in train.py.
|
||||
|
||||
# [ModelZoo Homepage](#contents)
|
||||
|
||||
# [ModelZoo Homepage](#contents)
|
||||
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).
|
||||
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@
|
|||
# ============================================================================
|
||||
|
||||
echo "======================================================================================================================================================="
|
||||
echo "Please run the scipt as: "
|
||||
echo "Please run the script as: "
|
||||
echo "sh run_distribute_train.sh DEVICE_NUM EPOCH_SIZE MINDRECORD_DIR IMAGE_DIR ANNO_PATH RANK_TABLE_FILE PRE_TRAINED PRE_TRAINED_EPOCH_SIZE"
|
||||
echo "For example: sh run_distribute_train.sh 8 150 /data/Mindrecord_train /data /data/train.txt /data/hccl.json /opt/yolov3-150.ckpt(optional) 100(optional)"
|
||||
echo "It is better to use absolute path."
|
||||
|
|
@ -47,7 +47,7 @@ then
|
|||
exit 1
|
||||
fi
|
||||
|
||||
echo "After running the scipt, the network runs in the background. The log will be generated in LOGx/log.txt"
|
||||
echo "After running the script, the network runs in the background. The log will be generated in LOGx/log.txt"
|
||||
|
||||
export RANK_TABLE_FILE=$6
|
||||
export RANK_SIZE=$1
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@
|
|||
# ============================================================================
|
||||
|
||||
echo "=============================================================================================================="
|
||||
echo "Please run the scipt as: "
|
||||
echo "Please run the script as: "
|
||||
echo "sh run_eval.sh DEVICE_ID CKPT_PATH MINDRECORD_DIR IMAGE_DIR ANNO_PATH"
|
||||
echo "for example: sh run_eval.sh 0 yolo.ckpt ./Mindrecord_eval ./dataset ./dataset/eval.txt"
|
||||
echo "=============================================================================================================="
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@
|
|||
# ============================================================================
|
||||
|
||||
echo "========================================================================================================================================="
|
||||
echo "Please run the scipt as: "
|
||||
echo "Please run the script as: "
|
||||
echo "sh run_standalone_train.sh DEVICE_ID EPOCH_SIZE MINDRECORD_DIR IMAGE_DIR ANNO_PATH PRE_TRAINED PRE_TRAINED_EPOCH_SIZE"
|
||||
echo "for example: sh run_standalone_train.sh 0 50 ./Mindrecord_train ./dataset ./dataset/train.txt /opt/yolov3-50.ckpt(optional) 30(optional)"
|
||||
echo "========================================================================================================================================="
|
||||
|
|
|
|||
Loading…
Reference in New Issue