From a7b93e04ec9e9ae5797f3b1de264c84b9b82eb06 Mon Sep 17 00:00:00 2001 From: ceci3 Date: Thu, 13 Feb 2020 17:44:37 +0800 Subject: [PATCH] fix bugs (#110) --- demo/nas/block_sa_nas_mobilenetv2.py | 26 ++++++++++--------------- demo/nas/sa_nas_mobilenetv2.py | 28 +++++++++++---------------- docs/en/model_zoo_en.md | 29 ++++++++++++++++++++++++---- docs/zh_cn/api_cn/nas_api.rst | 4 +++- docs/zh_cn/model_zoo.md | 26 ++++++++++++++++++++++--- paddleslim/nas/sa_nas.py | 5 ++++- 6 files changed, 76 insertions(+), 42 deletions(-) diff --git a/demo/nas/block_sa_nas_mobilenetv2.py b/demo/nas/block_sa_nas_mobilenetv2.py index 27fb1f4c..e4572583 100644 --- a/demo/nas/block_sa_nas_mobilenetv2.py +++ b/demo/nas/block_sa_nas_mobilenetv2.py @@ -16,13 +16,6 @@ import imagenet_reader _logger = get_logger(__name__, level=logging.INFO) -reduce_rate = 0.85 -init_temperature = 10.24 -max_flops = 321208544 -server_address = "" -port = 8979 -retain_epoch = 5 - def create_data_loader(image_shape): data_shape = [None] + image_shape @@ -71,17 +64,13 @@ def search_mobilenetv2_block(config, args, image_size): if args.is_server: sa_nas = SANAS( config, - server_addr=("", port), - init_temperature=init_temperature, - reduce_rate=reduce_rate, + server_addr=(args.server_address, args.port), search_steps=args.search_steps, is_server=True) else: sa_nas = SANAS( config, - server_addr=(server_address, port), - init_temperature=init_temperature, - reduce_rate=reduce_rate, + server_addr=(args.server_address, args.port), search_steps=args.search_steps, is_server=False) @@ -140,7 +129,7 @@ def search_mobilenetv2_block(config, args, image_size): current_flops = flops(train_program) print('step: {}, current_flops: {}'.format(step, current_flops)) - if current_flops > max_flops: + if current_flops > int(321208544): continue place = fluid.CUDAPlace(0) if args.use_gpu else fluid.CPUPlace() @@ -178,7 +167,7 @@ def search_mobilenetv2_block(config, args, image_size): train_compiled_program = fluid.CompiledProgram( train_program).with_data_parallel( loss_name=avg_cost.name, build_strategy=build_strategy) - for epoch_id in range(retain_epoch): + for epoch_id in range(args.retain_epoch): for batch_id, data in enumerate(train_loader()): fetches = [avg_cost.name] s_time = time.time() @@ -243,6 +232,11 @@ if __name__ == '__main__': type=int, default=100, help='controller server number.') + parser.add_argument( + '--server_address', type=str, default="", help='server ip.') + parser.add_argument('--port', type=int, default=8881, help='server port') + parser.add_argument( + '--retain_epoch', type=int, default=5, help='epoch for each token.') parser.add_argument('--lr', type=float, default=0.1, help='learning rate.') args = parser.parse_args() print(args) @@ -257,7 +251,7 @@ if __name__ == '__main__': args.data)) # block mask means block number, 1 mean downsample, 0 means the size of feature map don't change after this block - config_info = {'block_mask': [0, 1, 1, 1, 1, 0, 1, 0]} + config_info = {'block_mask': [0, 1, 1, 1, 0]} config = [('MobileNetV2BlockSpace', config_info)] search_mobilenetv2_block(config, args, image_size) diff --git a/demo/nas/sa_nas_mobilenetv2.py b/demo/nas/sa_nas_mobilenetv2.py index e6abe115..3adef135 100644 --- a/demo/nas/sa_nas_mobilenetv2.py +++ b/demo/nas/sa_nas_mobilenetv2.py @@ -18,13 +18,6 @@ import imagenet_reader _logger = get_logger(__name__, level=logging.INFO) -reduce_rate = 0.85 -init_temperature = 10.24 -max_flops = 321208544 -server_address = "" -port = 8989 -retain_epoch = 5 - def create_data_loader(image_shape): data_shape = [None] + image_shape @@ -66,18 +59,14 @@ def search_mobilenetv2(config, args, image_size, is_server=True): ### start a server and a client sa_nas = SANAS( config, - server_addr=("", port), - init_temperature=init_temperature, - reduce_rate=reduce_rate, + server_addr=(args.server_address, args.port), search_steps=args.search_steps, is_server=True) else: ### start a client sa_nas = SANAS( config, - server_addr=(server_address, port), - init_temperature=init_temperature, - reduce_rate=reduce_rate, + server_addr=(args.server_address, args.port), search_steps=args.search_steps, is_server=False) @@ -93,7 +82,7 @@ def search_mobilenetv2(config, args, image_size, is_server=True): current_flops = flops(train_program) print('step: {}, current_flops: {}'.format(step, current_flops)) - if current_flops > max_flops: + if current_flops > int(321208544): continue test_loader, test_avg_cost, test_acc_top1, test_acc_top5 = build_program( @@ -139,7 +128,7 @@ def search_mobilenetv2(config, args, image_size, is_server=True): train_compiled_program = fluid.CompiledProgram( train_program).with_data_parallel( loss_name=avg_cost.name, build_strategy=build_strategy) - for epoch_id in range(retain_epoch): + for epoch_id in range(args.retain_epoch): for batch_id, data in enumerate(train_loader()): fetches = [avg_cost.name] s_time = time.time() @@ -179,7 +168,7 @@ def search_mobilenetv2(config, args, image_size, is_server=True): def test_search_result(tokens, image_size, args, config): sa_nas = SANAS( config, - server_addr=("", 8887), + server_addr=(args.server_address, args.port), init_temperature=args.init_temperature, reduce_rate=args.reduce_rate, search_steps=args.search_steps, @@ -234,7 +223,7 @@ def test_search_result(tokens, image_size, args, config): train_compiled_program = fluid.CompiledProgram( train_program).with_data_parallel( loss_name=avg_cost.name, build_strategy=build_strategy) - for epoch_id in range(retain_epoch): + for epoch_id in range(args.retain_epoch): for batch_id, data in enumerate(train_loader()): fetches = [avg_cost.name] s_time = time.time() @@ -298,6 +287,11 @@ if __name__ == '__main__': type=int, default=100, help='controller server number.') + parser.add_argument( + '--server_address', type=str, default="", help='server ip.') + parser.add_argument('--port', type=int, default=8881, help='server port') + parser.add_argument( + '--retain_epoch', type=int, default=5, help='epoch for each token.') parser.add_argument('--lr', type=float, default=0.1, help='learning rate.') args = parser.parse_args() print(args) diff --git a/docs/en/model_zoo_en.md b/docs/en/model_zoo_en.md index caa6426e..47155978 100644 --- a/docs/en/model_zoo_en.md +++ b/docs/en/model_zoo_en.md @@ -16,7 +16,7 @@ Dataset：ImageNet1000 | MobileNetV2 | quant_aware |72.05%/90.63% (-0.1%/-0.02%)| 4.0 | - | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/MobileNetV2_quant_aware.tar) | |ResNet50|-|76.50%/93.00%| 99 | 2.71 | [model](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar) | |ResNet50|quant_post|76.33%/93.02% (-0.17%/+0.02%)| 25.1| 1.19 | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/ResNet50_quant_post.tar) | -|ResNet50|quant_aware| 76.48%/93.11% (-0.02%/+0.11%)| 25.1 | 1.17 | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/ResNet50_quant_awre.tar) | +|ResNet50|quant_aware| 76.48%/93.11% (-0.02%/+0.11%)| 25.1 | 1.17 | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/ResNet50_quant_awre.tar) | PaddleLite latency(ms) @@ -90,6 +90,13 @@ PaddleLite latency(ms) [1]：The `_vd` suffix indicates that the pre-trained model uses Mixup. Please refer to the detailed introduction: [mixup: Beyond Empirical Risk Minimization](https://arxiv.org/abs/1710.09412) +### 1.4 NAS + +| Model | Method | Top-1/Top-5 Acc | Volume（MB） | GFLOPs | Download | +|:--:|:---:|:--:|:--:|:--:|:--:| +| MobileNetV2 | - | 72.15%/90.65% | 15 | 0.59 | [model](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | +| MobileNetV2 | SANAS | 71.518%/90.208% (-0.632%/-0.442%) | 14 | 0.295 | [model](https://paddlemodels.cdn.bcebos.com/PaddleSlim/MobileNetV2_sanas.tar) | + ## 2. Object Detection ### 2.1 Quantization @@ -99,8 +106,8 @@ Dataset： COCO 2017 | Model | Method | Dataset | Image/GPU | Input 608 Box AP | Input 416 Box AP | Input 320 Box AP | Model Size（MB） | TensorRT latency(V100, ms) | Download | | :----------------------------: | :---------: | :----: | :-------: | :------------: | :------------: | :------------: | :------------: | :----------: |:----------: | | MobileNet-V1-YOLOv3 | - | COCO | 8 | 29.3 | 29.3 | 27.1 | 95 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | -| MobileNet-V1-YOLOv3 | quant_post | COCO | 8 | 27.9 (-1.4)| 28.0 (-1.3) | 26.0 (-1.0) | 25 | - | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) | -| MobileNet-V1-YOLOv3 | quant_aware | COCO | 8 | 28.1 (-1.2)| 28.2 (-1.1) | 25.8 (-1.2) | 26.3 | - | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenet_coco_quant_aware.tar) | +| MobileNet-V1-YOLOv3 | quant_post | COCO | 8 | 27.9 (-1.4)| 28.0 (-1.3) | 26.0 (-1.0) | 25 | - | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) | +| MobileNet-V1-YOLOv3 | quant_aware | COCO | 8 | 28.1 (-1.2)| 28.2 (-1.1) | 25.8 (-1.2) | 26.3 | - | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenet_coco_quant_aware.tar) | | R34-YOLOv3 | - | COCO | 8 | 36.2 | 34.3 | 31.4 | 162 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | | R34-YOLOv3 | quant_post | COCO | 8 | 35.7 (-0.5) | - | - | 42.7 | - | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_post.tar) | | R34-YOLOv3 | quant_aware | COCO | 8 | 35.2 (-1.0) | 33.3 (-1.0) | 30.3 (-1.1)| 44 | - | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) | @@ -157,8 +164,22 @@ Dataset：Pasacl VOC & COCO 2017 | MobileNet-V1-YOLOv3 | ResNet34-YOLOv3 distill | COCO | 8 | 31.4 (+2.1) | 30.0 (+0.7) | 27.1 (+0.1) | 95 | [model](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar) | -## 3. Image Segmentation +### 2.4 NAS + +Dataset: WIDER-FACE + +| Model | Method | Image/GPU | Input size | Easy/Medium/Hard | volume（KB） | latency（ms）| Download | +| :------------: | :---------: | :-------: | :------: | :-----------------------------: | :------------: | :------------: | :----------------------------------------------------------: | +| BlazeFace | - | 8 | 640 | 91.5/89.2/79.7 | 815 | 71.862 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) | +| BlazeFace-NAS | - | 8 | 640 | 83.7/80.7/65.8 | 244 | 21.117 |[model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) | +| BlazeFace-NAS1 | SANAS | 8 | 640 | 87.0/83.7/68.5 | 389 | 22.558 | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) | + +!!! note "Note" + + [1]: latency is based on latency_855.txt, the file is test on 855 by PaddleLite。 + +## 3. Image Segmentation Dataset：Cityscapes ### 3.1 Quantization diff --git a/docs/zh_cn/api_cn/nas_api.rst b/docs/zh_cn/api_cn/nas_api.rst index f1f0214d..d5ddaa58 100644 --- a/docs/zh_cn/api_cn/nas_api.rst +++ b/docs/zh_cn/api_cn/nas_api.rst @@ -128,7 +128,7 @@ SANAS（Simulated Annealing Neural Architecture Search）是基于模拟退火 - **tokens(list):** - 一组tokens。tokens的长度和范围取决于搜索空间。 **返回：** - 根据传入的token得到一个模型结构实例。 + 根据传入的token得到一个模型结构实例列表。 **示例代码：** @@ -153,8 +153,10 @@ SANAS（Simulated Annealing Neural Architecture Search）是基于模拟退火 **示例代码：** .. code-block:: python + import paddle.fluid as fluid from paddleslim.nas import SANAS config = [('MobileNetV2Space')] sanas = SANAS(configs=config) print(sanas.current_info()) + diff --git a/docs/zh_cn/model_zoo.md b/docs/zh_cn/model_zoo.md index 52987c6a..7414ac26 100644 --- a/docs/zh_cn/model_zoo.md +++ b/docs/zh_cn/model_zoo.md @@ -16,7 +16,7 @@ | MobileNetV2 | quant_aware |72.05%/90.63% (-0.1%/-0.02%)| 4.0 | - | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/MobileNetV2_quant_aware.tar) | |ResNet50|-|76.50%/93.00%| 99 | 2.71 | [下载链接](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar) | |ResNet50|quant_post|76.33%/93.02% (-0.17%/+0.02%)| 25.1| 1.19 | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/ResNet50_quant_post.tar) | -|ResNet50|quant_aware| 76.48%/93.11% (-0.02%/+0.11%)| 25.1 | 1.17 | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/ResNet50_quant_awre.tar) | +|ResNet50|quant_aware| 76.48%/93.11% (-0.02%/+0.11%)| 25.1 | 1.17 | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/ResNet50_quant_awre.tar) | 分类模型Lite时延(ms) @@ -89,6 +89,12 @@ [1]：带_vd后缀代表该预训练模型使用了Mixup，Mixup相关介绍参考[mixup: Beyond Empirical Risk Minimization](https://arxiv.org/abs/1710.09412) +### 1.4 搜索 + +| 模型 | 压缩方法 | Top-1/Top-5 Acc | 模型体积（MB） | GFLOPs | 下载 | +|:--:|:---:|:--:|:--:|:--:|:--:| +| MobileNetV2 | - | 72.15%/90.65% | 15 | 0.59 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | +| MobileNetV2 | SANAS | 71.518%/90.208% (-0.632%/-0.442%) | 14 | 0.295 | [下载链接](https://paddlemodels.cdn.bcebos.com/PaddleSlim/MobileNetV2_sanas.tar) | ## 2. 目标检测 @@ -99,8 +105,8 @@ | 模型 | 压缩方法 | 数据集 | Image/GPU | 输入608 Box AP | 输入416 Box AP | 输入320 Box AP | 模型体积（MB） | TensorRT时延(V100, ms) | 下载 | | :----------------------------: | :---------: | :----: | :-------: | :------------: | :------------: | :------------: | :------------: | :----------: |:----------: | | MobileNet-V1-YOLOv3 | - | COCO | 8 | 29.3 | 29.3 | 27.1 | 95 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) | -| MobileNet-V1-YOLOv3 | quant_post | COCO | 8 | 27.9 (-1.4)| 28.0 (-1.3) | 26.0 (-1.0) | 25 | - | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) | -| MobileNet-V1-YOLOv3 | quant_aware | COCO | 8 | 28.1 (-1.2)| 28.2 (-1.1) | 25.8 (-1.2) | 26.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenet_coco_quant_aware.tar) | +| MobileNet-V1-YOLOv3 | quant_post | COCO | 8 | 27.9 (-1.4)| 28.0 (-1.3) | 26.0 (-1.0) | 25 | - | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) | +| MobileNet-V1-YOLOv3 | quant_aware | COCO | 8 | 28.1 (-1.2)| 28.2 (-1.1) | 25.8 (-1.2) | 26.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenet_coco_quant_aware.tar) | | R34-YOLOv3 | - | COCO | 8 | 36.2 | 34.3 | 31.4 | 162 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) | | R34-YOLOv3 | quant_post | COCO | 8 | 35.7 (-0.5) | - | - | 42.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_post.tar) | | R34-YOLOv3 | quant_aware | COCO | 8 | 35.2 (-1.0) | 33.3 (-1.0) | 30.3 (-1.1)| 44 | - | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) | @@ -157,6 +163,20 @@ | MobileNet-V1-YOLOv3 | ResNet34-YOLOv3 distill | COCO | 8 | 31.4 (+2.1) | 30.0 (+0.7) | 27.1 (+0.1) | 95 | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar) | +### 2.4 搜索 + +数据集：WIDER-FACE + +| 模型 | 压缩方法 | Image/GPU | 输入尺寸 | Easy/Medium/Hard | 模型体积（KB） | 硬件延时（ms）| 下载 | +| :------------: | :---------: | :-------: | :------: | :-----------------------------: | :------------: | :------------: | :----------------------------------------------------------: | +| BlazeFace | - | 8 | 640 | 91.5/89.2/79.7 | 815 | 71.862 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) | +| BlazeFace-NAS | - | 8 | 640 | 83.7/80.7/65.8 | 244 | 21.117 |[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) | +| BlazeFace-NAS1 | SANAS | 8 | 640 | 87.0/83.7/68.5 | 389 | 22.558 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) | + +!!! note "Note" + + [1]: 硬件延时时间是利用提供的硬件延时表得到的，硬件延时表是在855芯片上基于PaddleLite测试的结果。 + ## 3. 图像分割 数据集：Cityscapes diff --git a/paddleslim/nas/sa_nas.py b/paddleslim/nas/sa_nas.py index 679ecca4..8e97aee6 100644 --- a/paddleslim/nas/sa_nas.py +++ b/paddleslim/nas/sa_nas.py @@ -190,7 +190,10 @@ class SANAS(object): self._iter = 0 def _get_host_ip(self): - return socket.gethostbyname(socket.gethostname()) + if os.name == 'posix': + return socket.gethostbyname('localhost') + else: + return socket.gethostbyname(socket.gethostname()) def tokens2arch(self, tokens): """ -- GitLab