From f4060607df8a3f4edaf9d7eaeabb8e9d3bc288c6 Mon Sep 17 00:00:00 2001 From: zhanghuiyao <1814619459@qq.com> Date: Wed, 23 Dec 2020 17:03:09 +0800 Subject: [PATCH] Modify resnet50_adv_pruning network to fix mindspore 1.0.0 version --- .../cv/resnet50_adv_pruning/Readme.md | 47 ++++++++++--------- .../research/cv/resnet50_adv_pruning/eval.py | 19 ++++---- .../cv/resnet50_adv_pruning/src/config.py | 20 +------- .../resnet50_adv_pruning/src/pet_dataset.py | 11 +++-- .../resnet50_adv_pruning/src/resnet_imgnet.py | 14 +++--- 5 files changed, 47 insertions(+), 64 deletions(-) diff --git a/model_zoo/research/cv/resnet50_adv_pruning/Readme.md b/model_zoo/research/cv/resnet50_adv_pruning/Readme.md index 59c4e8395f5..d15ec5e63a1 100644 --- a/model_zoo/research/cv/resnet50_adv_pruning/Readme.md +++ b/model_zoo/research/cv/resnet50_adv_pruning/Readme.md @@ -4,14 +4,14 @@ - [Dataset](#dataset) - [Environment Requirements](#environment-requirements) - [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Training Process](#training-process) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) + - [Script and Sample Code](#script-and-sample-code) + - [Training Process](#training-process) + - [Evaluation Process](#evaluation-process) + - [Evaluation](#evaluation) - [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) + - [Performance](#performance) + - [Training Performance](#evaluation-performance) + - [Inference Performance](#evaluation-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -26,20 +26,20 @@ The Adversarial Pruning method is a reliable neural network pruning algorithm by Dataset used: [Oxford-IIIT Pet](https://www.robots.ox.ac.uk/~vgg/data/pets/) - Dataset size: 7049 colorful images in 1000 classes - - Train: 3680 images - - Test: 3369 images + - Train: 3680 images + - Test: 3369 images - Data format: RGB images. - - Note: Data will be processed in src/dataset.py + - Note: Data will be processed in src/dataset.py # [Environment Requirements](#contents) - Hardware（Ascend/GPU） - - Prepare hardware environment with Ascend or GPU 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 or GPU 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) + - [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) + - [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) @@ -58,6 +58,7 @@ Dataset used: [Oxford-IIIT Pet](https://www.robots.ox.ac.uk/~vgg/data/pets/) ``` ## [Training process](#contents) + To Be Done ## [Eval process](#contents) @@ -66,12 +67,11 @@ To Be Done After installing MindSpore via the official website, you can start evaluation as follows: - ### Launch -``` -# infer example - +```bash + # infer example + Ascend: python eval.py --dataset_path ~/Pets/test.mindrecord --platform Ascend --checkpoint_path [CHECKPOINT_PATH] GPU: python eval.py --dataset_path ~/Pets/test.mindrecord --platform GPU --checkpoint_path [CHECKPOINT_PATH] ``` @@ -80,18 +80,18 @@ After installing MindSpore via the official website, you can start evaluation as ### Result -``` +```python result: {'acc': 0.8023984736985554} ckpt= ./resnet50-imgnet-0.65x-80.24.ckpt - ``` # [Model Description](#contents) ## [Performance](#contents) -#### Evaluation Performance +### Evaluation Performance + +#### ResNet50-0.65x on ImageNet2012 -###### ResNet50-0.65x on ImageNet2012 | Parameters | | | -------------------------- | -------------------------------------- | | Model Version | ResNet50-0.65x | @@ -102,7 +102,8 @@ result: {'acc': 0.8023984736985554} ckpt= ./resnet50-imgnet-0.65x-80.24.ckpt | FLOPs (G) | 2.1 | | Accuracy (Top1) | 75.80 | -###### ResNet50-0.65x on Oxford-IIIT Pet +#### ResNet50-0.65x on Oxford-IIIT Pet + | Parameters | | | -------------------------- | -------------------------------------- | | Model Version | ResNet50-0.65x | diff --git a/model_zoo/research/cv/resnet50_adv_pruning/eval.py b/model_zoo/research/cv/resnet50_adv_pruning/eval.py index 7d8e33cb473..fe9370e42da 100644 --- a/model_zoo/research/cv/resnet50_adv_pruning/eval.py +++ b/model_zoo/research/cv/resnet50_adv_pruning/eval.py @@ -26,7 +26,7 @@ from mindspore.train.serialization import load_checkpoint, load_param_into_net from mindspore.common import dtype as mstype from src.pet_dataset import create_dataset -from src.config import config_ascend, config_gpu +from src.config import cfg from src.resnet_imgnet import resnet50 @@ -40,14 +40,12 @@ args_opt = parser.parse_args() if __name__ == '__main__': - config_platform = None + config_platform = cfg if args_opt.platform == "Ascend": - config_platform = config_ascend device_id = int(os.getenv('DEVICE_ID')) context.set_context(mode=context.GRAPH_MODE, device_target="Ascend", device_id=device_id, save_graphs=False) elif args_opt.platform == "GPU": - config_platform = config_gpu context.set_context(mode=context.GRAPH_MODE, device_target="GPU", save_graphs=False) else: @@ -55,12 +53,6 @@ if __name__ == '__main__': loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean') - if args_opt.platform == "Ascend": - net.to_float(mstype.float16) - for _, cell in net.cells_and_names(): - if isinstance(cell, nn.Dense): - cell.to_float(mstype.float32) - dataset = create_dataset(dataset_path=args_opt.dataset_path, do_train=False, config=config_platform, @@ -76,6 +68,13 @@ if __name__ == '__main__': net = resnet50( rate=0.65, class_num=config_platform.num_classes, index=index) + + if args_opt.platform == "Ascend": + net.to_float(mstype.float16) + for _, cell in net.cells_and_names(): + if isinstance(cell, nn.Dense): + cell.to_float(mstype.float32) + if args_opt.checkpoint_path: param_dict = load_checkpoint(args_opt.checkpoint_path) load_param_into_net(net, param_dict) diff --git a/model_zoo/research/cv/resnet50_adv_pruning/src/config.py b/model_zoo/research/cv/resnet50_adv_pruning/src/config.py index 6eb39510bfd..53312a4fba6 100644 --- a/model_zoo/research/cv/resnet50_adv_pruning/src/config.py +++ b/model_zoo/research/cv/resnet50_adv_pruning/src/config.py @@ -17,25 +17,7 @@ network config setting, will be used in train.py and eval.py """ from easydict import EasyDict as ed -config_ascend = ed({ - "num_classes": 438, - "image_height": 224, - "image_width": 224, - "batch_size": 256, - "epoch_size": 200, - "warmup_epochs": 1, - "lr": 0.02, - "momentum": 0.9, - "weight_decay": 4e-5, - "label_smooth": 0.1, - "loss_scale": 1024, - "save_checkpoint": True, - "save_checkpoint_epochs": 5, - "keep_checkpoint_max": 200, - "save_checkpoint_path": "./checkpoint", -}) - -config_gpu = ed({ +cfg = ed({ "num_classes": 37, "image_height": 224, "image_width": 224, diff --git a/model_zoo/research/cv/resnet50_adv_pruning/src/pet_dataset.py b/model_zoo/research/cv/resnet50_adv_pruning/src/pet_dataset.py index 88b8b637a56..e72ea607d96 100644 --- a/model_zoo/research/cv/resnet50_adv_pruning/src/pet_dataset.py +++ b/model_zoo/research/cv/resnet50_adv_pruning/src/pet_dataset.py @@ -18,10 +18,11 @@ create train or eval dataset. import os import mindspore.common.dtype as mstype import mindspore.dataset.engine as de -import mindspore.dataset.transforms.vision.c_transforms as C -import mindspore.dataset.transforms.vision.py_transforms as P +import mindspore.dataset.vision.c_transforms as C +import mindspore.dataset.vision.py_transforms as P import mindspore.dataset.transforms.c_transforms as C2 -from mindspore.dataset.transforms.vision import Inter +import mindspore.dataset.transforms.py_transforms as P2 +from mindspore.dataset.vision import Inter def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch_size=100): @@ -78,13 +79,13 @@ def create_dataset(dataset_path, do_train, config, platform, repeat_num=1, batch center_crop_p = P.CenterCrop(224) totensor = P.ToTensor() normalize_p = P.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)) - composeop = P.ComposeOp( + composeop = P2.Compose( [decode_p, resize_p, center_crop_p, totensor, normalize_p]) if do_train: trans = [resize_crop_op, horizontal_flip_op, color_op, rescale_op, normalize_op, change_swap_op] else: - trans = composeop() + trans = composeop type_cast_op = C2.TypeCast(mstype.int32) ds = ds.map(input_columns="image", operations=trans, diff --git a/model_zoo/research/cv/resnet50_adv_pruning/src/resnet_imgnet.py b/model_zoo/research/cv/resnet50_adv_pruning/src/resnet_imgnet.py index 05cf4abd006..3c086895c25 100644 --- a/model_zoo/research/cv/resnet50_adv_pruning/src/resnet_imgnet.py +++ b/model_zoo/research/cv/resnet50_adv_pruning/src/resnet_imgnet.py @@ -327,21 +327,21 @@ class ResNet(nn.Cell): for _, m in self.cells_and_names(): if isinstance(m, (nn.Conv2d)): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels - m.weight.set_parameter_data(Tensor(np.random.normal(0, np.sqrt(2. / n), - m.weight.data.shape).astype("float32"))) + m.weight.set_data(Tensor(np.random.normal(0, np.sqrt(2. / n), + m.weight.data.shape).astype("float32"))) if m.bias is not None: - m.bias.set_parameter_data( + m.bias.set_data( Tensor(np.zeros(m.bias.data.shape, dtype="float32"))) elif isinstance(m, nn.BatchNorm2d): - m.gamma.set_parameter_data( + m.gamma.set_data( Tensor(np.ones(m.gamma.data.shape, dtype="float32"))) - m.beta.set_parameter_data( + m.beta.set_data( Tensor(np.zeros(m.beta.data.shape, dtype="float32"))) elif isinstance(m, nn.Dense): - m.weight.set_parameter_data(Tensor(np.random.normal( + m.weight.set_data(Tensor(np.random.normal( 0, 0.01, m.weight.data.shape).astype("float32"))) if m.bias is not None: - m.bias.set_parameter_data( + m.bias.set_data( Tensor(np.zeros(m.bias.data.shape, dtype="float32")))