From 5e41760f73596a03d22c16244b97c4515feb429c Mon Sep 17 00:00:00 2001 From: Zeng Jinle <32832641+sneaxiy@users.noreply.github.com> Date: Mon, 2 Sep 2019 14:03:14 +0800 Subject: [PATCH] remove memory optimize usage in scripts, test=develop (#3242) --- PaddleCV/image_classification/README.md | 4 -- PaddleCV/image_classification/README_cn.md | 4 -- .../dist_train/dist_train.py | 1 - PaddleCV/image_classification/run.sh | 53 ------------------- PaddleCV/image_classification/train.py | 2 - PaddleNLP/Research/ACL2019-JEMT/README.md | 1 - 6 files changed, 65 deletions(-) diff --git a/PaddleCV/image_classification/README.md b/PaddleCV/image_classification/README.md index d7b4fe7b..f5c9982d 100644 --- a/PaddleCV/image_classification/README.md +++ b/PaddleCV/image_classification/README.md @@ -68,7 +68,6 @@ python train.py \ --class_dim=1000 \ --image_shape=3,224,224 \ --model_save_dir=output/ \ - --with_mem_opt=False \ --with_inplace=True \ --lr_strategy=piecewise_decay \ --lr=0.1 @@ -83,7 +82,6 @@ python train.py \ * **class_dim**: the class number of the classification task. Default: 1000. * **image_shape**: input size of the network. Default: "3,224,224". * **model_save_dir**: the directory to save trained model. Default: "output". -* **with_mem_opt**: whether to use memory optimization or not. Default: False. * **with_inplace**: whether to use inplace memory optimization or not. Default: True. * **lr_strategy**: learning rate changing strategy. Default: "piecewise_decay". * **lr**: initialized learning rate. Default: 0.1. @@ -154,8 +152,6 @@ Note: Add and adjust other parameters accroding to specific models and tasks. You may add `--fp16=1` to start train using mixed precisioin training, which the training process will use float16 and the output model ("master" parameters) is saved as float32. You also may need to pass `--scale_loss` to overcome accuracy issues, usually `--scale_loss=8.0` will do. -Note that currently `--fp16` can not use together with `--with_mem_opt`, so pass `--with_mem_opt=0` to disable memory optimization pass. - ### CE CE is only for internal testing, don't have to set it. diff --git a/PaddleCV/image_classification/README_cn.md b/PaddleCV/image_classification/README_cn.md index ec17a708..83128c65 100644 --- a/PaddleCV/image_classification/README_cn.md +++ b/PaddleCV/image_classification/README_cn.md @@ -64,7 +64,6 @@ python train.py \ --class_dim=1000 \ --image_shape=3,224,224 \ --model_save_dir=output/ \ - --with_mem_opt=False \ --with_inplace=True \ --lr_strategy=piecewise_decay \ --lr=0.1 @@ -79,7 +78,6 @@ python train.py \ * **class_dim**: 类别数，默认值: 1000 * **image_shape**: 图片大小，默认值: "3,224,224" * **model_save_dir**: 模型存储路径，默认值: "output/" -* **with_mem_opt**: 是否开启显存优化，默认值: False * **with_inplace**: 是否开启inplace显存优化，默认值: True * **lr_strategy**: 学习率变化策略，默认值: "piecewise_decay" * **lr**: 初始学习率，默认值: 0.1 @@ -142,8 +140,6 @@ python infer.py \ 可以通过开启`--fp16=True`启动混合精度训练，这样训练过程会使用float16数据，并输出float32的模型参数（"master"参数）。您可能需要同时传入`--scale_loss`来解决fp16训练的精度问题，通常传入`--scale_loss=8.0`即可。 -注意，目前混合精度训练不能和内存优化功能同时使用，所以需要传`--with_mem_opt=False`这个参数来禁用内存优化功能。 - ### CE测试 注意：CE相关代码仅用于内部测试，enable_ce默认设置False。 diff --git a/PaddleCV/image_classification/dist_train/dist_train.py b/PaddleCV/image_classification/dist_train/dist_train.py index 11c9063f..fb21e4fa 100644 --- a/PaddleCV/image_classification/dist_train/dist_train.py +++ b/PaddleCV/image_classification/dist_train/dist_train.py @@ -46,7 +46,6 @@ def parse_args(): add_arg('class_dim', int, 1000, "Class number.") add_arg('image_shape', str, "3,224,224", "input image size") add_arg('model_save_dir', str, "output", "model save directory") - add_arg('with_mem_opt', bool, False, "Whether to use memory optimization or not.") add_arg('pretrained_model', str, None, "Whether to use pretrained model.") add_arg('checkpoint', str, None, "Whether to resume checkpoint.") add_arg('lr', float, 0.1, "set learning rate.") diff --git a/PaddleCV/image_classification/run.sh b/PaddleCV/image_classification/run.sh index b2466a79..ad04260d 100644 --- a/PaddleCV/image_classification/run.sh +++ b/PaddleCV/image_classification/run.sh @@ -7,7 +7,6 @@ python train.py \ --class_dim=1000 \ --image_shape=3,224,224 \ --model_save_dir=output/ \ - --with_mem_opt=True \ --lr_strategy=cosine_decay \ --lr=0.1 \ --num_epochs=200 \ @@ -22,7 +21,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=piecewise_decay \ # --num_epochs=120 \ # --lr=0.01 \ @@ -39,7 +37,6 @@ python train.py \ # --model_save_dir=output/ \ # --lr=0.02 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --l2_decay=1e-4 #SqueezeNet1_1 @@ -53,7 +50,6 @@ python train.py \ # --model_save_dir=output/ \ # --lr=0.02 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --l2_decay=1e-4 #VGG11: @@ -67,7 +63,6 @@ python train.py \ # --model_save_dir=output/ \ # --lr=0.1 \ # --num_epochs=90 \ -# --with_mem_opt=True \ # --l2_decay=2e-4 #VGG13: @@ -81,7 +76,6 @@ python train.py \ # --lr=0.01 \ # --num_epochs=90 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --l2_decay=3e-4 #VGG16: @@ -95,7 +89,6 @@ python train.py \ # --model_save_dir=output/ \ # --lr=0.01 \ # --num_epochs=90 \ -# --with_mem_opt=True \ # --l2_decay=3e-4 #VGG19: @@ -108,7 +101,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.01 \ # --num_epochs=90 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=3e-4 @@ -120,7 +112,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=piecewise_decay \ # --num_epochs=120 \ # --lr=0.1 \ @@ -134,7 +125,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --num_epochs=240 \ # --lr=0.1 \ @@ -150,7 +140,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --num_epochs=240 \ # --lr=0.1 \ @@ -166,7 +155,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --num_epochs=240 \ # --lr=0.1 \ @@ -180,7 +168,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --num_epochs=240 \ # --lr=0.1 \ @@ -194,7 +181,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --num_epochs=240 \ # --lr=0.1 \ @@ -208,7 +194,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_warmup_decay \ # --num_epochs=240 \ # --lr=0.5 \ @@ -225,7 +210,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_warmup_decay \ # --num_epochs=240 \ # --lr=0.5 \ @@ -242,7 +226,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_warmup_decay \ # --num_epochs=240 \ # --lr=0.5 \ @@ -259,7 +242,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_warmup_decay \ # --num_epochs=240 \ # --lr=0.5 \ @@ -274,7 +256,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_warmup_decay \ # --num_epochs=240 \ # --lr=0.25 \ @@ -290,7 +271,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_warmup_decay \ # --num_epochs=240 \ # --lr=0.25 \ @@ -304,7 +284,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_warmup_decay \ # --lr=0.5 \ # --num_epochs=240 \ @@ -318,7 +297,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=120 \ @@ -332,7 +310,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=120 \ @@ -346,7 +323,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=piecewise_decay \ # --num_epochs=120 \ # --lr=0.1 \ @@ -362,7 +338,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ @@ -376,7 +351,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=7e-5 \ # --use_mixup=True \ @@ -391,7 +365,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=piecewise_decay \ # --num_epochs=120 \ # --lr=0.1 \ @@ -407,7 +380,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -423,7 +395,6 @@ python train.py \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ # --lr_strategy=piecewise_decay \ -# --with_mem_opt=True \ # --lr=0.1 \ # --num_epochs=120 \ # --l2_decay=1e-4 @@ -438,7 +409,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -455,7 +425,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -472,7 +441,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -486,7 +454,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -503,7 +470,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -517,7 +483,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -534,7 +499,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -548,7 +512,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=15e-5 @@ -562,7 +525,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -579,7 +541,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -593,7 +554,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=18e-5 @@ -607,7 +567,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -621,7 +580,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -635,7 +593,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -649,7 +606,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -663,7 +619,6 @@ python train.py \ # --lr_strategy=piecewise_decay \ # --lr=0.1 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 @@ -678,7 +633,6 @@ python train.py \ # --model_save_dir=output/ \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --l2_decay=1.2e-4 #SE_ResNeXt101_32x4d: @@ -692,7 +646,6 @@ python train.py \ # --model_save_dir=output/ \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --l2_decay=1.5e-5 # SE_154 @@ -705,7 +658,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -720,7 +672,6 @@ python train.py \ # --class_dim=1000 \ # --image_shape=3,224,224 \ # --model_save_dir=output/ \ -# --with_mem_opt=True \ # --lr_strategy=cosine_decay \ # --lr=0.01 \ # --num_epochs=200 \ @@ -736,7 +687,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.045 \ # --num_epochs=120 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --resize_short_size=320 @@ -751,7 +701,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.045 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -769,7 +718,6 @@ python train.py \ # --lr_strategy=cosine_decay \ # --lr=0.1 \ # --num_epochs=200 \ -# --with_mem_opt=True \ # --model_save_dir=output/ \ # --l2_decay=1e-4 \ # --use_mixup=True \ @@ -787,7 +735,6 @@ python train.py \ # --image_shape=3,224,224 \ # --lr=0.001 \ # --num_epochs=120 \ -# --with_mem_opt=False \ # --model_save_dir=output/ \ # --lr_strategy=adam \ # --use_gpu=False diff --git a/PaddleCV/image_classification/train.py b/PaddleCV/image_classification/train.py index 48428bec..6f9563dc 100755 --- a/PaddleCV/image_classification/train.py +++ b/PaddleCV/image_classification/train.py @@ -443,8 +443,6 @@ def train(args): use_ngraph = os.getenv('FLAGS_use_ngraph') if not use_ngraph: build_strategy = fluid.BuildStrategy() - # memopt may affect GC results - #build_strategy.memory_optimize = args.with_mem_opt build_strategy.enable_inplace = args.with_inplace #build_strategy.fuse_all_reduce_ops=1 diff --git a/PaddleNLP/Research/ACL2019-JEMT/README.md b/PaddleNLP/Research/ACL2019-JEMT/README.md index b003b9a2..73e4c02c 100644 --- a/PaddleNLP/Research/ACL2019-JEMT/README.md +++ b/PaddleNLP/Research/ACL2019-JEMT/README.md @@ -81,7 +81,6 @@ beta代表发音信息的权重。这表明，即使将绝大部分权重放在 --sort_type pool \ --pool_size 200000 \ --use_py_reader False \ - --use_mem_opt False \ --enable_ce False \ --fetch_steps 1 \ pass_num 100 \ -- GitLab