[英]TensorFlow on Windows 10 with Anaconda & Python 3.6
Let me start by saying I am a beginner on Deep Learning and trying to find my way by following the Tensorflow tutorial, which is mainly applying the inception V3 method to the flowers data set. 首先,我要说我是深度学习的初学者,然后尝试通过Tensorflow教程寻找方法,该教程主要将Inception V3方法应用于flowers数据集。
https://www.tensorflow.org/tutorials/image_retraining https://www.tensorflow.org/tutorials/image_retraining
which includes the following : 其中包括以下内容:
cd ~ 光盘〜
curl -O (flower data link) -- runs fine curl -O(花数据链接)- 运行正常
tar xzf flower_photos.tgz -- runs fine tar xzf flower_photos.tgz- 运行正常
bazel build tensorflow/examples/image_retraining:retrain --error: no bazel command found bazel构建tensorflow / examples / image_retraining:retrain --error:找不到bazel命令
In order to be able to follow this tutorial, I have also completed the Tensorflow installation tutorial and modified (replaced 35 to 36) it for Python 3.6 compatible whl as follows: pip install --ignore-installed --upgrade https://storage.googleapis.com/tensorflow/windows/cpu/tensorflow-1.2.1-cp36-cp36m-win_amd64.whl 为了能够遵循本教程,我还完成了Tensorflow安装教程,并对其进行了修改(将其替换为35至36),以便与Python 3.6兼容,如下所示:pip install --ignore-installed --upgrade https:// storage .googleapis.com / tensorflow /窗/ CPU / tensorflow-1.2.1- CP36-cp36m-win_amd64.whl
Now back to the main question: After installing the flower data set and installing the bazel package, cygwin64. 现在回到主要问题:安装花数据集并安装bazel软件包cygwin64之后。 I went into the Bazel folder and ran the configure file as suggested in the forums as well as touch WORKSPACE and bagel build.
我进入Bazel文件夹并按照论坛中的建议运行配置文件,并触摸WORKSPACE和百吉饼构建。 When I run the command "bazel build tensorflow/examples/image_retraining:retrain" I still get the error: "Bazel command not found"
当我运行命令“ bazel build tensorflow / examples / image_retraining:retrain”时,我仍然收到错误:“找不到Bazel命令”
I followed similar questions on stackoverflow before openning up my own question, such as: questions- 41791171/bazel-build-for-tensorflow-inception-model and git clone'd the entire Tensorflow folder as instructed but resulted an eror of :bagel: command not found 在提出自己的问题之前,我在stackoverflow上遵循了类似的问题,例如:问题41791171 / bazel-build-for-tensorflow-inception-model和git按照指示克隆了整个Tensorflow文件夹,但导致了:bagel错误:找不到相关命令
To summarize, how can I run the Tensorflow Flowerset tutorial and overcome the errors of :bagel: command not found and :bazel: command not found? 总而言之,我该如何运行Tensorflow Flowerset教程并克服:bagel:命令未找到和:bazel:命令未找到的错误?
It's not mandatory to use Bazel for the TensorFlow Image Retraining tutorial . TensorFlow Image Retraining教程不是必须使用Bazel 。
You can also run the retrain.py located in the \\tensorflow\\examples\\image_retraining\\ folder cloned from the TensorFlow GitHub repo to retrain the Inception v3 model or Mobilenet model. 您还可以运行位于从TensorFlow GitHub库克隆重新调校该盗梦空间V3模型或Mobilenet模型\\ tensorflow \\例子\\ image_retraining \\文件夹中的retrain.py。
https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/examples/image_retraining/retrain.py https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/examples/image_retraining/retrain.py
Put the Flowers datasets folder ( flower_photos ) under the image_retraining and run the retrain.py as below: 将鲜花数据集文件夹( flower_photos )放在image_retraining下,然后运行retrain.py,如下所示:
python retrain.py --image_dir flower_photos
You should see the script will download the Inception v3 model. 您应该看到脚本将下载Inception v3模型。
The image retraining in progress. 正在进行图像再训练。
After the retraining is completed, you should see the below: 重新培训完成后,您应该看到以下内容:
Copy both output_graph.pb and output_labels.txt in the C:\\tmp folder, which are the retrain outputs to the image_retraining folder. 将output_graph.pb和output_labels.txt复制到C:\\ tmp文件夹中,它们是再训练输出到image_retraining文件夹。
To verify the retrained model, you can run the label_image.py as below. 要验证重新训练的模型,可以按如下所示运行label_image.py 。 It should show the top 5 predictions.
它应该显示前5个预测。
python label_image.py --image=flower_photos\daisy\21652746_cc379e0eea_m.jpg --graph=output_graph.pb --labels=output_labels.txt
The expected output should be as below: 预期输出应如下所示:
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.