Add benchmark (fps) in MODEL_ZOO doc (#3263)

* Add benchmark (fps) in MODEL_ZOO doc

ppdet/utils/eval_utils.py

@@ -19,6 +19,7 @@ from __future__ import print_function
 import logging
 import numpy as np
 import os
+import time
 
 import paddle.fluid as fluid
 
@@ -69,6 +70,10 @@ def eval_run(exe, compile_program, pyreader, keys, values, cls):
             cls[i].reset(exe)
             values.append(accum_map)
 
+    images_num = 0
+    start_time = time.time()
+    has_bbox = 'bbox' in keys
+
     try:
         pyreader.start()
         while True:
@@ -83,10 +88,20 @@ def eval_run(exe, compile_program, pyreader, keys, values, cls):
             if iter_id % 100 == 0:
                 logger.info('Test iter {}'.format(iter_id))
             iter_id += 1
+            images_num += len(res['bbox'][1][0]) if has_bbox else 1
     except (StopIteration, fluid.core.EOFException):
         pyreader.reset()
     logger.info('Test finish iter {}'.format(iter_id))
 
+    end_time = time.time()
+    fps = images_num / (end_time - start_time)
+    if has_bbox:
+        logger.info('Total number of images: {}, inference time: {} fps.'.
+                    format(images_num, fps))
+    else:
+        logger.info('Total iteration: {}, inference time: {} batch/s.'.format(
+            images_num, fps))
+
     return results
 
 
@@ -114,7 +129,10 @@ def eval_results(results,
             if output_directory:
                 output = os.path.join(output_directory, 'bbox.json')
 
-            box_ap_stats = bbox_eval(results, anno_file, output,
+            box_ap_stats = bbox_eval(
+                results,
+                anno_file,
+                output,
                 with_background,
                 is_bbox_normalized=is_bbox_normalized)
 
@@ -130,7 +148,8 @@ def eval_results(results,
             box_ap_stats.append(res * 100.)
         elif 'bbox' in results[0]:
             box_ap = voc_bbox_eval(
-                results, num_classes, 
+                results,
+                num_classes,
                 is_bbox_normalized=is_bbox_normalized,
                 map_type=map_type)
             box_ap_stats.append(box_ap)

tools/eval.py

@@ -17,7 +17,6 @@ from __future__ import division
 from __future__ import print_function
 
 import os
-import multiprocessing
 
 
 def set_paddle_flags(**kwargs):
@@ -63,12 +62,6 @@ def main():
     # check if set use_gpu=True in paddlepaddle cpu version
     check_gpu(cfg.use_gpu)
 
-    if cfg.use_gpu:
-        devices_num = fluid.core.get_cuda_device_count()
-    else:
-        devices_num = int(
-            os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
-
     if 'eval_feed' not in cfg:
         eval_feed = create(main_arch + 'EvalFeed')
     else:
@@ -100,15 +93,9 @@ def main():
         json_eval_results(
             eval_feed, cfg.metric, json_directory=FLAGS.output_eval)
         return
-    # compile program for multi-devices
-    if devices_num <= 1:
-        compile_program = fluid.compiler.CompiledProgram(eval_prog)
-    else:
-        build_strategy = fluid.BuildStrategy()
-        build_strategy.memory_optimize = False
-        build_strategy.enable_inplace = False
+
     compile_program = fluid.compiler.CompiledProgram(
-            eval_prog).with_data_parallel(build_strategy=build_strategy)
+        eval_prog).with_data_parallel()
 
     # load model
     exe.run(startup_prog)
@@ -132,6 +119,7 @@ def main():
         is_bbox_normalized = model.is_bbox_normalized()
 
     results = eval_run(exe, compile_program, pyreader, keys, values, cls)
+
     # evaluation
     resolution = None
     if 'mask' in results[0]:

tools/train.py

@@ -18,16 +18,17 @@ from __future__ import print_function
 
 import os
 import time
-import multiprocessing
 import numpy as np
 import datetime
 from collections import deque
 
+
 def set_paddle_flags(**kwargs):
     for key, value in kwargs.items():
         if os.environ.get(key, None) is None:
             os.environ[key] = str(value)
 
+
 # NOTE(paddle-dev): All of these flags should be set before 
 # `import paddle`. Otherwise, it would not take any effect.
 set_paddle_flags(
@@ -69,8 +70,7 @@ def main():
     if cfg.use_gpu:
         devices_num = fluid.core.get_cuda_device_count()
     else:
-        devices_num = int(
-            os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
+        devices_num = int(os.environ.get('CPU_NUM', 1))
 
     if 'train_feed' not in cfg:
         train_feed = create(main_arch + 'TrainFeed')
@@ -133,12 +133,10 @@ def main():
 
     # compile program for multi-devices
     build_strategy = fluid.BuildStrategy()
-    build_strategy.memory_optimize = False
     build_strategy.enable_inplace = False
     sync_bn = getattr(model.backbone, 'norm_type', None) == 'sync_bn'
     # only enable sync_bn in multi GPU devices
-    build_strategy.sync_batch_norm = sync_bn and devices_num > 1 \
-         and cfg.use_gpu
+    build_strategy.sync_batch_norm = sync_bn and devices_num > 1 and cfg.use_gpu
     train_compile_program = fluid.compiler.CompiledProgram(
         train_prog).with_data_parallel(
             loss_name=loss.name, build_strategy=build_strategy)
@@ -202,14 +200,16 @@ def main():
                 resolution = None
                 if 'mask' in results[0]:
                     resolution = model.mask_head.resolution
-                box_ap_stats = eval_results(results, eval_feed, cfg.metric, cfg.num_classes,
-                             resolution, is_bbox_normalized, FLAGS.output_eval, map_type)
+                box_ap_stats = eval_results(
+                    results, eval_feed, cfg.metric, cfg.num_classes, resolution,
+                    is_bbox_normalized, FLAGS.output_eval, map_type)
                 if box_ap_stats[0] > best_box_ap_list[0]:
                     best_box_ap_list[0] = box_ap_stats[0]
                     best_box_ap_list[1] = it
-                    checkpoint.save(exe, train_prog, os.path.join(save_dir,"best_model"))
+                    checkpoint.save(exe, train_prog,
+                                    os.path.join(save_dir, "best_model"))
                 logger.info("Best test box ap: {}, in iter: {}".format(
-                    best_box_ap_list[0],best_box_ap_list[1]))
+                    best_box_ap_list[0], best_box_ap_list[1]))
 
     train_pyreader.reset()