update benchmark info

Author: TingquanGao

docs/module_usage/instructions/benchmark.md

@@ -6,7 +6,7 @@ PaddleX 支持统计模型推理耗时，需通过环境变量进行设置，具
 * `PADDLE_PDX_INFER_BENCHMARK_WARMUP`：设置 warm up，在开始测试前，使用随机数据循环迭代 n 次，默认为 `0`；
 * `PADDLE_PDX_INFER_BENCHMARK_DATA_SIZE`： 设置随机数据的尺寸，默认为 `224`；
 * `PADDLE_PDX_INFER_BENCHMARK_ITER`：使用随机数据进行 Benchmark 测试的循环次数，仅当输入数据为 `None` 时，将使用随机数据进行测试；
-* `PADDLE_PDX_INFER_BENCHMARK_OUTPUT`：用于设置保存本次 benchmark 指标到 `txt` 文件，如 `./benchmark.txt`，默认为 `None`，表示不保存 Benchmark 指标；
+* `PADDLE_PDX_INFER_BENCHMARK_OUTPUT`：用于设置保存的目录，如 `./benchmark`，默认为 `None`，表示不保存 Benchmark 指标；
 
 使用示例如下：
 
@@ -15,55 +15,60 @@ PADDLE_PDX_INFER_BENCHMARK=True \
 PADDLE_PDX_INFER_BENCHMARK_WARMUP=5 \
 PADDLE_PDX_INFER_BENCHMARK_DATA_SIZE=320 \
 PADDLE_PDX_INFER_BENCHMARK_ITER=10 \
-PADDLE_PDX_INFER_BENCHMARK_OUTPUT=./benchmark.txt \
+PADDLE_PDX_INFER_BENCHMARK_OUTPUT=./benchmark \
 python main.py \
     -c ./paddlex/configs/object_detection/PicoDet-XS.yaml \
     -o Global.mode=predict \
     -o Predict.model_dir=None \
+    -o Predict.batch_size=2 \
     -o Predict.input=None
 ```
 
 在开启 Benchmark 后，将自动打印 benchmark 指标：
 
 ```
-+----------------+-----------------+------+---------------+
-|     Stage      | Total Time (ms) | Nums | Avg Time (ms) |
-+----------------+-----------------+------+---------------+
-|    ReadCmp     |   185.48870087  |  10  |  18.54887009  |
-|     Resize     |   16.95227623   |  30  |   0.56507587  |
-|   Normalize    |   41.12100601   |  30  |   1.37070020  |
-|   ToCHWImage   |    0.05745888   |  30  |   0.00191530  |
-|    Copy2GPU    |   14.58549500   |  10  |   1.45854950  |
-|     Infer      |   100.14462471  |  10  |  10.01446247  |
-|    Copy2CPU    |    9.54508781   |  10  |   0.95450878  |
-| DetPostProcess |    0.56767464   |  30  |   0.01892249  |
-+----------------+-----------------+------+---------------+
-+-------------+-----------------+------+---------------+
-|    Stage    | Total Time (ms) | Nums | Avg Time (ms) |
-+-------------+-----------------+------+---------------+
-|  PreProcess |   243.61944199  |  30  |   8.12064807  |
-|  Inference  |   124.27520752  |  30  |   4.14250692  |
-| PostProcess |    0.56767464   |  30  |   0.01892249  |
-|   End2End   |   379.70948219  |  30  |  12.65698274  |
-|    WarmUp   |  9465.68179131  |  5   | 1893.13635826 |
-+-------------+-----------------+------+---------------+
++----------------+-----------------+-----------------+------------------------+
+|   Component    | Total Time (ms) | Number of Calls | Avg Time Per Call (ms) |
++----------------+-----------------+-----------------+------------------------+
+|    ReadCmp     |   102.39458084  |        10       |      10.23945808       |
+|     Resize     |   11.20400429   |        20       |       0.56020021       |
+|   Normalize    |   34.11078453   |        20       |       1.70553923       |
+|   ToCHWImage   |    0.05555153   |        20       |       0.00277758       |
+|    Copy2GPU    |    9.10568237   |        10       |       0.91056824       |
+|     Infer      |   98.22225571   |        10       |       9.82222557       |
+|    Copy2CPU    |   14.30845261   |        10       |       1.43084526       |
+| DetPostProcess |    0.45251846   |        20       |       0.02262592       |
++----------------+-----------------+-----------------+------------------------+
++-------------+-----------------+---------------------+----------------------------+
+|    Stage    | Total Time (ms) | Number of Instances | Avg Time Per Instance (ms) |
++-------------+-----------------+---------------------+----------------------------+
+|  PreProcess |   147.76492119  |          20         |         7.38824606         |
+|  Inference  |   121.63639069  |          20         |         6.08181953         |
+| PostProcess |    0.45251846   |          20         |         0.02262592         |
+|   End2End   |   294.03519630  |          20         |        14.70175982         |
+|    WarmUp   |  7937.82591820  |          5          |       1587.56518364        |
++-------------+-----------------+---------------------+----------------------------+
 ```
 
-在 Benchmark 结果中，会统计该模型全部组件（`Component`）的总耗时（`Total Time`，单位为“毫秒”）、**调用次数**（`Nums`）、**调用**平均执行耗时（`Avg Time`，单位为“毫秒”），以及按预热（`WarmUp`）、预处理（`PreProcess`）、模型推理（`Inference`）、后处理（`PostProcess`）和端到端（`End2End`）进行划分的耗时统计，包括每个阶段的总耗时（`Total Time`，单位为“毫秒”）、**样本数**（`Nums`）和**单样本**平均执行耗时（`Avg Time`，单位为“毫秒”），同时，保存相关指标会到本地 `./benchmark.csv` 文件中：
+在 Benchmark 结果中，会统计该模型全部组件（`Component`）的总耗时（`Total Time`，单位为“毫秒”）、**调用次数**（`Number of Calls`）、**调用**平均执行耗时（`Avg Time Per Call`，单位“毫秒”），以及按预热（`WarmUp`）、预处理（`PreProcess`）、模型推理（`Inference`）、后处理（`PostProcess`）和端到端（`End2End`）进行划分的耗时统计，包括每个阶段的总耗时（`Total Time`，单位为“毫秒”）、**样本数**（`Number of Instances`）和**单样本**平均执行耗时（`Avg Time Per Instance`，单位“毫秒”），同时，上述指标会保存到到本地： `./benchmark/detail.csv` 和 `./benchmark/summary.csv`：
 
 ```csv
-Stage,Total Time (ms),Nums,Avg Time (ms)
-ReadCmp,0.18548870086669922,10,0.018548870086669923
-Resize,0.0169522762298584,30,0.0005650758743286133
-Normalize,0.04112100601196289,30,0.001370700200398763
-ToCHWImage,5.745887756347656e-05,30,1.915295918782552e-06
-Copy2GPU,0.014585494995117188,10,0.0014585494995117188
-Infer,0.10014462471008301,10,0.0100144624710083
-Copy2CPU,0.009545087814331055,10,0.0009545087814331055
-DetPostProcess,0.0005676746368408203,30,1.892248789469401e-05
-PreProcess,0.24361944198608398,30,0.0081206480662028
-Inference,0.12427520751953125,30,0.0041425069173177086
-PostProcess,0.0005676746368408203,30,1.892248789469401e-05
-End2End,0.37970948219299316,30,0.012656982739766438
-WarmUp,9.465681791305542,5,1.8931363582611085
+Component,Total Time (ms),Number of Calls,Avg Time Per Call (ms)
+ReadCmp,0.10199093818664551,10,0.01019909381866455
+Resize,0.011309385299682617,20,0.0005654692649841309
+Normalize,0.035140275955200195,20,0.0017570137977600097
+ToCHWImage,4.744529724121094e-05,20,2.3722648620605467e-06
+Copy2GPU,0.00861215591430664,10,0.000861215591430664
+Infer,0.820899248123169,10,0.08208992481231689
+Copy2CPU,0.006002187728881836,10,0.0006002187728881836
+DetPostProcess,0.0004436969757080078,20,2.218484878540039e-05
+```
+
+```csv
+Stage,Total Time (ms),Number of Instance,Avg Time Per Instance (ms)
+PreProcess,0.14848804473876953,20,0.007424402236938477
+Inference,0.8355135917663574,20,0.04177567958831787
+PostProcess,0.0004436969757080078,20,2.218484878540039e-05
+End2End,1.0054960250854492,20,0.05027480125427246
+WarmUp,8.869974851608276,5,1.7739949703216553
 ```

paddlex/configs/object_detection/PicoDet-S.yaml

@@ -33,7 +33,7 @@ Export:
   weight_path: https://paddledet.bj.bcebos.com/models/picodet_s_320_coco_lcnet.pdparams
 
 Predict:
-  batch_size: 3
+  batch_size: 1
   model_dir: "output/best_model/inference"
   input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
   kernel_option:

paddlex/inference/utils/benchmark.py

@@ -16,6 +16,7 @@
 import functools
 from types import GeneratorType
 import time
+from pathlib import Path
 import numpy as np
 from prettytable import PrettyTable
 
@@ -116,8 +117,13 @@ def collect(self, e2e_num):
         self._e2e_elapse = time.time() - self._e2e_tic
         detail, summary = self.gather(e2e_num)
 
-        table_head = ["Stage", "Total Time (ms)", "Nums", "Avg Time (ms)"]
-        table = PrettyTable(table_head)
+        detail_head = [
+            "Component",
+            "Total Time (ms)",
+            "Number of Calls",
+            "Avg Time Per Call (ms)",
+        ]
+        table = PrettyTable(detail_head)
         table.add_rows(
             [
                 (name, f"{total * 1000:.8f}", cnts, f"{avg * 1000:.8f}")
@@ -126,7 +132,13 @@ def collect(self, e2e_num):
         )
         logging.info(table)
 
-        table = PrettyTable(table_head)
+        summary_head = [
+            "Stage",
+            "Total Time (ms)",
+            "Number of Instances",
+            "Avg Time Per Instance (ms)",
+        ]
+        table = PrettyTable(summary_head)
         table.add_rows(
             [
                 (name, f"{total * 1000:.8f}", cnts, f"{avg * 1000:.8f}")
@@ -136,10 +148,17 @@ def collect(self, e2e_num):
         logging.info(table)
 
         if INFER_BENCHMARK_OUTPUT:
-            csv_data = [table_head]
-            csv_data.extend(detail)
-            csv_data.extend(summary)
-            with open("benchmark.csv", "w", newline="") as file:
+            save_dir = Path(INFER_BENCHMARK_OUTPUT)
+            save_dir.mkdir(parents=True, exist_ok=True)
+            csv_data = [detail_head, *detail]
+            # csv_data.extend(detail)
+            with open(Path(save_dir) / "detail.csv", "w", newline="") as file:
+                writer = csv.writer(file)
+                writer.writerows(csv_data)
+
+            csv_data = [summary_head, *summary]
+            # csv_data.extend(summary)
+            with open(Path(save_dir) / "summary.csv", "w", newline="") as file:
                 writer = csv.writer(file)
                 writer.writerows(csv_data)