From 7710199dd4885c39d133477daf6eb2eb3baf660b Mon Sep 17 00:00:00 2001 From: latyas Date: Tue, 22 Jan 2019 00:04:34 +0800 Subject: [PATCH] add english readme --- README.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/README.md b/README.md index db701f2..193e04c 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,15 @@ Tensorflow Workspace for K210 ====== ## Classifier for ImageNet +1. Download ImageNet dataset, extract it as the instructions to ILSVRC2012\_img\_train, it has 1000 folders, each folder's name represents its class id. +2. The model definition file is `mobilenetv1/models/mobilenet_v1.py`, **ATTENTION**, K210 does not support the method of *SAME PADDING* in tensorflow, so we need to add padding around the image manually before a `stride=2` conv (in this situation, the padding method of conv layer with `stride=2` should be set to *VALID* +3. Modify `mobilenetv1/run_mobilenet_v1.sh` and start your training. +4. Using `freeze_graph.py` to freeze your model from `ckpt` to `pb`, just run `python mobilenetv1/freeze_graph.py model.mobilenet_v1 ckpt_fold pb_file` +5. Test on ImageNet, you need a val dataset of ImageNet, then run `python mobilenetv1/validation_imagenet.py pb_file val_set_fold` +6. Estimate one image, run `python mobilenetv1/predict_one_pic.py pb_file pic` + + +## ImageNet 分类器示例 1. 下载ImageNet数据集，按照说明解压缩训练数据集到文件夹ILSVRC2012\_img\_train，内含1000个子文件夹，每个子文件夹的命名为其分类代号（类似n02484975），每个子文件夹内为该分类的训练数据 2. mobilenet v1定义文件：mobilenetv1/models/mobilenet\_v1.py，需要注意由于K210不支持tensorflow的SAME padding，所以在stride=2时先固定padding一圈0，然后再进行stride=2的卷积（padding=VALID） 3. 训练脚本 mobilenetv1/run\_mobilenet\_v1.sh，根据需要修改其中的参数，然后运行