gpt4 book ai didi

tensorflow - Tensorboard 没有显示最后一个检查点的评估结果

转载 作者:行者123 更新时间:2023-12-03 16:29:14 25 4
gpt4 key购买 nike

我使用 TensorFlow 对象检测 API 使用自定义数据训练了一些对象检测模型,步长为 4K,并在​​训练期间对其进行了评估。已对所有检查点进行评估,我在控制台上查看了结果。

但是由于某些原因,我在Tensorboard上看不到最后两个checkpoints的评估结果。它显示了 3K 步的评估结果,之后什么都没有。我可以在控制台和文件夹中看到评估已完成。

当我启动 Tensorboard 时,控制台上没有任何错误消息。可以看到训练结果已经全部上传到Tensorboard,唯一缺少的就是上次的评估结果。

我尝试再次评估最新的检查点,但没有任何改变。在评估结束时,我收到一条消息,说指标已记录到摘要...

训练检查点每 10 分钟保存一次,评估需要 12 分钟。但即使在这种情况下,我也希望最新的检查点的评估结果在那里。

当我尝试从 Tensorboard 下载 csv 文件时,我也看不到最后两个检查点的评估。

可能是什么原因?

I0311 16:57:21.281645 MainThread program.py:165] Not bringing up TensorBoard, but inspecting event files.
I0311 16:57:21.281645 140028330256128 program.py:165] Not bringing up TensorBoard, but inspecting event files.
======================================================================
Processing event files... (this can take a few minutes)
======================================================================

Found event files in:
./CN_flow1_95/eval
./CN_flow1_95/train

These tags are in ./CN_flow1_95/eval:
audio -
histograms -
images
image-0
image-1
image-2
image-3
image-4
image-5
image-6
image-7
image-8
image-9
scalars
Losses/Loss/BoxClassifierLoss/classification_loss
Losses/Loss/BoxClassifierLoss/localization_loss
Losses/Loss/RPNLoss/localization_loss
Losses/Loss/RPNLoss/objectness_loss
PascalBoxes_PerformanceByCategory/AP@0.5IOU/b'cyclist'
PascalBoxes_PerformanceByCategory/AP@0.5IOU/b'motorcyclist'
PascalBoxes_PerformanceByCategory/AP@0.5IOU/b'pedestrian'
PascalBoxes_Precision/mAP@0.5IOU
tensor -
======================================================================

Event statistics for ./CN_flow1_95/eval:
audio -
graph
first_step 0
last_step 0
max_step 0
min_step 0
num_steps 1
outoforder_steps []
histograms -
images
first_step 0
last_step 4112
max_step 4112
min_step 0
num_steps 7
outoforder_steps []
scalars
first_step 0
last_step 4112
max_step 4112
min_step 0
num_steps 7
outoforder_steps []
sessionlog:checkpoint -
sessionlog:start -
sessionlog:stop -
tensor -
======================================================================

These tags are in ./CN_flow1_95/train:
audio -
histograms
ModelVars/...
images -
scalars
Losses/TotalLoss
Losses/clone_0/Loss/BoxClassifierLoss/classification_loss
Losses/clone_0/Loss/BoxClassifierLoss/localization_loss
Losses/clone_0/Loss/RPNLoss/localization_loss
Losses/clone_0/Loss/RPNLoss/objectness_loss
Losses/clone_1/Loss/BoxClassifierLoss/classification_loss
Losses/clone_1/Loss/BoxClassifierLoss/localization_loss
Losses/clone_1/Loss/RPNLoss/localization_loss
Losses/clone_1/Loss/RPNLoss/objectness_loss
Losses/clone_2/Loss/BoxClassifierLoss/classification_loss
Losses/clone_2/Loss/BoxClassifierLoss/localization_loss
Losses/clone_2/Loss/RPNLoss/localization_loss
Losses/clone_2/Loss/RPNLoss/objectness_loss
batch/fraction_of_150_full
clone_0/Losses/clone_0//clone_loss
global_step/sec
queue/prefetch_queue/fraction_of_5_full
tensor -
======================================================================

Event statistics for ./CN_flow1_95/train:
audio -
graph
first_step 0
last_step 0
max_step 0
min_step 0
num_steps 1
outoforder_steps []
histograms
first_step 0
last_step 4110
max_step 4110
min_step 0
num_steps 28
outoforder_steps []
images -
scalars
first_step 0
last_step 4110
max_step 4110
min_step 0
num_steps 54
outoforder_steps []
sessionlog:checkpoint
first_step 1
last_step 4111
max_step 4111
min_step 1
num_steps 7
outoforder_steps []
sessionlog:start
outoforder_steps []
steps [0, 4110]
sessionlog:stop
outoforder_steps []
steps [0, 0]
tensor -
======================================================================

最佳答案

我也在 TensorBoard repo 上问过这个问题。他们说没有理由不完美加载事件文件,让我来这里...

有时会看到正确的结果(如果由于详尽的测试而有 10-15 个事件文件),但大多数情况下看不到。我更改了存储检查点的频率,以便在评估期间不会遗漏任何检查点(没有意义,但仍然尝试过)

我每 12 分钟存储一次检查点,因为评估也需要 12 分钟。它也没有用。

所有 tensorboard --inspect 结果看起来都很好。

我在不同的电脑上尝试了不同的机型,也清理了浏览器缓存。没有任何帮助。

我相信 tensorboard 中存在错误。

关于tensorflow - Tensorboard 没有显示最后一个检查点的评估结果,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/55101924/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com