From 737ba38d1fdf0cfe0599c77e25d6aa5498821476 Mon Sep 17 00:00:00 2001 From: julie Date: Sat, 16 Sep 2017 14:56:29 -0700 Subject: [PATCH] Single Shot MultiBox Detector English README --- ssd/README.md | 4 ++-- ssd/index.html | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/ssd/README.md b/ssd/README.md index 666f5572..9be7b34f 100644 --- a/ssd/README.md +++ b/ssd/README.md @@ -76,7 +76,7 @@ The first field is the relative path of the image file, and the second field is We also provide a pre-trained model using VGG-16 with good performance. To use the model, download the file http://paddlepaddle.bj.bcebos.com/model_zoo/detection/ssd_model/vgg_model.tar.gz, and place it as ```vgg/vgg_model.tar.gz```。 ### Training -Next, run ```python train.py``` to train the model. Note that this example only supports the CUDA GPU environment, and can not be trained on only CPU. This is mainly because the training is very slow using CPU only. +Next, run ```python train.py``` to train the model. Note that this example only supports the CUDA GPU environment, and can not be trained using only CPU. This is mainly because the training is very slow using CPU only. ```python paddle.init(use_gpu=True, trainer_count=4) @@ -97,7 +97,7 @@ Below is a description about this script: 1. Call ```paddle.init``` with 4 GPUs. 2. ```data_provider.Settings()``` is to pass configuration parameters. For ```config/vgg_config.py``` setting，300x300 is a typical configuration for both the accuracy and efficiency. It can be extended to 512x512 by modifying the configuration file. 3. In ```train()```执 function, ```train_file_list``` specifies the training data list, and ```dev_file_list``` specifies the evaluation data list, and ```init_model_path``` specifies the pre-training model location. -4. During the training process will print some log information, each training a batch will output the current number of rounds, the current batch cost and mAP (mean Average Precision. Each training pass will be saved a model to the default saved directory ```heckpoints``` (Need to be created in advance). +4. During the training process will print some log information, each training a batch will output the current number of rounds, the current batch cost and mAP (mean Average Precision. Each training pass will be saved a model to the default saved directory ```checkpoints``` (Need to be created in advance). The following shows the SDD300x300 in the VOC data set. diff --git a/ssd/index.html b/ssd/index.html index 88a0216c..a667eda7 100644 --- a/ssd/index.html +++ b/ssd/index.html @@ -118,7 +118,7 @@ The first field is the relative path of the image file, and the second field is We also provide a pre-trained model using VGG-16 with good performance. To use the model, download the file http://paddlepaddle.bj.bcebos.com/model_zoo/detection/ssd_model/vgg_model.tar.gz, and place it as ```vgg/vgg_model.tar.gz```。 ### Training -Next, run ```python train.py``` to train the model. Note that this example only supports the CUDA GPU environment, and can not be trained on only CPU. This is mainly because the training is very slow using CPU only. +Next, run ```python train.py``` to train the model. Note that this example only supports the CUDA GPU environment, and can not be trained using only CPU. This is mainly because the training is very slow using CPU only. ```python paddle.init(use_gpu=True, trainer_count=4) @@ -139,7 +139,7 @@ Below is a description about this script: 1. Call ```paddle.init``` with 4 GPUs. 2. ```data_provider.Settings()``` is to pass configuration parameters. For ```config/vgg_config.py``` setting，300x300 is a typical configuration for both the accuracy and efficiency. It can be extended to 512x512 by modifying the configuration file. 3. In ```train()```执 function, ```train_file_list``` specifies the training data list, and ```dev_file_list``` specifies the evaluation data list, and ```init_model_path``` specifies the pre-training model location. -4. During the training process will print some log information, each training a batch will output the current number of rounds, the current batch cost and mAP (mean Average Precision. Each training pass will be saved a model to the default saved directory ```heckpoints``` (Need to be created in advance). +4. During the training process will print some log information, each training a batch will output the current number of rounds, the current batch cost and mAP (mean Average Precision. Each training pass will be saved a model to the default saved directory ```checkpoints``` (Need to be created in advance). The following shows the SDD300x300 in the VOC data set. -- GitLab