小编Lin*_*ang的帖子

我遵循了 sentdex 的 Tensorflow 对象检测教程。参考网站.... https://pythonprogramming.net/introduction-use-tensorflow-object-detection-api-tutorial/
我已经成功得到了结果。现在我想在训练后可视化权重。像这样.... https://medium.com/@awjuliani/visualizing-neural-network-layer-activation-tensorflow-tutorial-d45f8bf7bbc4 ..或.. https://gist.github.com/kukuruza/03731dc494603ceab0c5 .. 我尝试从 model_ckpt_meta 文件中获取一些权重信息。Model_ckpt_meta 文件有很多信息，但我不知道该选择哪一个。所以我选择其中一个信息。并尝试可视化权重。这是我的代码和结果？

import tensorflow as tf
import numpy as np
from tensorflow.python import pywrap_tensorflow
from matplotlib import pyplot as plt
with tf.Session() as sess:
  new_saver = tf.train.import_meta_graph(checkpoint_path + '.meta')
  new_saver.restore(sess, tf.train.latest_checkpoint(checkpoint_path))
  weightArray=sess.run('BoxPredictor_5/ClassPredictor/weights:0')
  weightArray = weightArray.reshape(-1,1,32,3)
  x_min = np.min(weightArray)
  x_max = np.max(weightArray)
  wing=255.0*(weightArray.squeeze() - x_min) / (x_max - x_min)
  plt.imshow(wing.astype('uint8'))
  plt.axis('off')

结果：

结果有什么办法显示的更清楚吗？如果使用 ssd_mobilenet 模型无法获得可视化权重。希望能告诉我。非常感谢。

我有一系列(.dcm)要转换为nii.gz文件的每位患者的 dicom 文件，但以下转换没有任何反应（甚至是错误信息）...

import dicom2nifti
dicom2nifti.settings.set_gdcmconv_path('C:/Program Files/GDCM 3.0/bin/gdcmconv.exe')
dicom2nifti.convert_directory('M0_1', 'M0_1.nii.gz')

尝试其他方法时出现错误......

import dicom2nifti
dicom2nifti.settings.set_gdcmconv_path('C:/Program Files/GDCM 3.0/bin/gdcmconv.exe')
dicom2nifti.dicom_series_to_nifti('M0_1', 'M0_1.nii.gz')

错误日志：

Traceback (most recent call last):
  File ".\test.py", line 5, in <module>
    dicom2nifti.dicom_series_to_nifti('M0_1', 'M0_1.nii.gz')
  File "D:\Anaconda3\envs\pydicom\lib\site-packages\dicom2nifti\convert_dicom.py", line 78, in dicom_series_to_nifti
    return dicom_array_to_nifti(dicom_input, output_file, reorient_nifti)
  File "D:\Anaconda3\envs\pydicom\lib\site-packages\dicom2nifti\convert_dicom.py", line 112, in dicom_array_to_nifti
    if not are_imaging_dicoms(dicom_list):
  File "D:\Anaconda3\envs\pydicom\lib\site-packages\dicom2nifti\convert_dicom.py", line 151, in are_imaging_dicoms
    if common.is_philips(dicom_input):
  File "D:\Anaconda3\envs\pydicom\lib\site-packages\dicom2nifti\common.py", line 102, in is_philips
    header = dicom_input[0]
IndexError: list index out of range

文件结构：

M0_1 …