Google的Inception-v3微调脚本中引发了错误 [英] Error thrown in Google's Inception-v3 fine-tuning script

问题描述

遵循自述文件对Google的Inception-v3图像分类模型进行了微调，但出现错误:

When following the Readme to fine-tune Google's Inception-v3 image classification model, I get the error:

文件"/Path/to/Model/bazel-bin/inception/flowers_train.runfiles/inception/inception/slim/ops.py"，第88行，在batch_norm中initializer = tf.zeros_initializer()，TypeError:zeros_initializer()至少接受1个参数(给定0个参数)

这是在运行最终命令后发生的:

This occurs after running the final command:

   bazel-bin/inception/flowers_train \
  --train_dir="${TRAIN_DIR}" \
  --data_dir="${FLOWERS_DATA_DIR}" \
  --pretrained_model_checkpoint_path="${MODEL_PATH}" \
  --fine_tune=True \
  --initial_learning_rate=0.001 \
  --input_queue_memory_factor=1

我有0个想法，这是怎么回事，因为此错误是从TF小组编写的python文件抛出的.另外，作为TF新手，我对自己的方法知之甚少，无法尝试进行深度调试会话.仅查看错误的路径，运行TF超薄代码的脚本可能存在问题吗?

I have 0 idea whats going on here as this error gets thrown from a python file written by the TF team. Additionally, being a TF newbie, I do not know my way around enough to attempt a deep debugging session. Just by looking at the path from the error, there might be an issue with the script running TF slim code?

无论如何，我正在使用Python 3.6和TensorFlow Python API r0.12运行macOS Sierra.

Anyhow, I am running macOS Sierra with Python 3.6 and the TensorFlow Python API r0.12.

推荐答案

因此，如果当前的tensorflow安装没有最新的tensorflow-slim代码，则会引发此错误.在此处安装说明.

So turns out this error was thrown if the current installation of tensorflow did not have the most recent tensorflow-slim code. Install directions here.

这篇关于Google的Inception-v3微调脚本中引发了错误的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！