mrg*_*oom 0 benchmarking tensorflow tensorflow-lite
Tensorflow 有几个基准测试工具:
我对 .pb 基准工具的参数有几个问题:
num_threads相关的单线程实验或通过使用tensorflow内螺纹平行运行次数?还有一些关于结果解释的问题:
count在结果输出?如何Timings (microseconds): count=相关--max_num_runs的参数?例子:
Run --num_threads=-1 --max_num_runs=1000:
2019-03-20 14:30:33.253584: I tensorflow/core/util/stat_summarizer.cc:85] Timings (microseconds): count=1000 first=3608 curr=3873 min=3566 max=8009 avg=3766.49 std=202
2019-03-20 14:30:33.253584: I tensorflow/core/util/stat_summarizer.cc:85] Memory (bytes): count=1000 curr=3301344(all same)
2019-03-20 14:30:33.253591: I tensorflow/core/util/stat_summarizer.cc:85] 207 nodes observed
2019-03-20 14:30:33.253597: I tensorflow/core/util/stat_summarizer.cc:85]
2019-03-20 14:30:33.378352: I tensorflow/tools/benchmark/benchmark_model.cc:636] FLOPs estimate: 116.65M
2019-03-20 14:30:33.378390: I tensorflow/tools/benchmark/benchmark_model.cc:638] FLOPs/second: 46.30B
Run --num_threads=1 --max_num_runs=1000:
2019-03-20 14:32:25.591915: I tensorflow/core/util/stat_summarizer.cc:85] Timings (microseconds): count=1000 first=7502 curr=7543 min=7495 max=7716 avg=7607.22 std=34
2019-03-20 14:32:25.591934: I tensorflow/core/util/stat_summarizer.cc:85] Memory (bytes): count=1000 curr=3301344(all same)
2019-03-20 14:32:25.591952: I tensorflow/core/util/stat_summarizer.cc:85] 207 nodes observed
2019-03-20 14:32:25.591970: I tensorflow/core/util/stat_summarizer.cc:85]
2019-03-20 14:32:25.805970: I tensorflow/tools/benchmark/benchmark_model.cc:636] FLOPs estimate: 116.65M
2019-03-20 14:32:25.806007: I tensorflow/tools/benchmark/benchmark_model.cc:638] FLOPs/second: 15.46B
Run --num_threads=-1 --max_num_runs=10000:
2019-03-20 14:38:48.045824: I tensorflow/core/util/stat_summarizer.cc:85] Timings (microseconds): count=3570 first=3961 curr=3899 min=3558 max=6997 avg=3841.2 std=175
2019-03-20 14:38:48.045829: I tensorflow/core/util/stat_summarizer.cc:85] Memory (bytes): count=3570 curr=3301344(all same)
2019-03-20 14:38:48.045833: I tensorflow/core/util/stat_summarizer.cc:85] 207 nodes observed
2019-03-20 14:38:48.045837: I tensorflow/core/util/stat_summarizer.cc:85]
2019-03-20 14:38:48.169368: I tensorflow/tools/benchmark/benchmark_model.cc:636] FLOPs estimate: 116.65M
2019-03-20 14:38:48.169412: I tensorflow/tools/benchmark/benchmark_model.cc:638] FLOPs/second: 48.66B
Run --num_threads=1 --max_num_runs=10000:
2019-03-20 14:35:50.826722: I tensorflow/core/util/stat_summarizer.cc:85] Timings (microseconds): count=1254 first=7496 curr=7518 min=7475 max=7838 avg=7577.23 std=50
2019-03-20 14:35:50.826735: I tensorflow/core/util/stat_summarizer.cc:85] Memory (bytes): count=1254 curr=3301344(all same)
2019-03-20 14:35:50.826746: I tensorflow/core/util/stat_summarizer.cc:85] 207 nodes observed
2019-03-20 14:35:50.826757: I tensorflow/core/util/stat_summarizer.cc:85]
2019-03-20 14:35:51.053143: I tensorflow/tools/benchmark/benchmark_model.cc:636] FLOPs estimate: 116.65M
2019-03-20 14:35:51.053180: I tensorflow/tools/benchmark/benchmark_model.cc:638] FLOPs/second: 15.55B
Run Code Online (Sandbox Code Playgroud)
即当--max_num_runs=10000使用计数count=3570和count=1254这是什么意思?
对于.tflite基准工具:
--num_threads=1 --num_runs=10000
Initialized session in 0.682ms
Running benchmark for at least 1 iterations and at least 0.5 seconds
count=54 first=23463 curr=8019 min=7911 max=23463 avg=9268.5 std=2995
Running benchmark for at least 1000 iterations and at least 1 seconds
count=1000 first=8022 curr=6703 min=6613 max=10333 avg=6766.23 std=337
Average inference timings in us: Warmup: 9268.5, Init: 682, no stats: 6766.23
Run Code Online (Sandbox Code Playgroud)
什么no stats: 6766.23意思?
在深入研究代码后,我发现了以下内容(所有时间都以微秒为单位):
count: 实际运行次数first: 第一次迭代所用的时间curr: 上次迭代的时间min: 迭代所需的最短时间max: 迭代花费的最长时间avg: 迭代平均时间std:所有运行时间的标准偏差Warmup: 预热运行平均值Init: 启动时间(应始终与 相同Initialized session in)no stats: 是名字很差的平均运行时间(与avg=前一行中的匹配)num_threads:这用于设置intra_op_parallelism_threads和inter_op_parallelism_threads(更多信息在这里)相关文件(链接到正确的行)是:
stats_calculator.h - 实际跟踪运行时的代码benchmark_model.cc(tflite) - 奇怪的“无统计数据”名称benchmark_model.cc(pb) - 使用 num_threads我不太确定使用 GPU 还是不使用 GPU。如果您使用freeze_graph导出.pb文件,那么它将在图中存储每个节点的设备。您可以在导出之前使用设备放置来执行此操作。如果您在尝试设置环境变量CUDA_VISIBLE_DEVICES=""以确保不使用 GPU后需要更改它。
| 归档时间: |
|
| 查看次数: |
1023 次 |
| 最近记录: |