Merge pull request #1097 from RainFrost1/benchmark

添加全链条自动化测试脚本

deploy/python/predict_cls.py

@@ -27,6 +27,7 @@ from utils.get_image_list import get_image_list
 from python.preprocess import create_operators
 from python.postprocess import build_postprocess
 
+
 class ClsPredictor(Predictor):
     def __init__(self, config):
         super().__init__(config["Global"])
@@ -40,6 +41,29 @@ class ClsPredictor(Predictor):
         if "PostProcess" in config:
             self.postprocess = build_postprocess(config["PostProcess"])
 
+        # for whole_chain project to test each repo of paddle
+        self.benchmark = config["Global"].get("benchmark", False)
+        if self.benchmark:
+            import auto_log
+            import os
+            pid = os.getpid()
+            self.auto_logger = auto_log.AutoLogger(
+                model_name=config["Global"].get("model_name", "cls"),
+                model_precision='fp16'
+                if config["Global"]["use_fp16"] else 'fp32',
+                batch_size=config["Global"].get("batch_size", 1),
+                data_shape=[3, 224, 224],
+                save_path=config["Global"].get("save_log_path",
+                                               "./auto_log.log"),
+                inference_config=self.config,
+                pids=pid,
+                process_name=None,
+                gpu_ids=None,
+                time_keys=[
+                    'preprocess_time', 'inference_time', 'postprocess_time'
+                ],
+                warmup=2)
+
     def predict(self, images):
         input_names = self.paddle_predictor.get_input_names()
         input_tensor = self.paddle_predictor.get_input_handle(input_names[0])
@@ -48,18 +72,26 @@ class ClsPredictor(Predictor):
         output_tensor = self.paddle_predictor.get_output_handle(output_names[
             0])
 
+        if self.benchmark:
+            self.auto_logger.times.start()
         if not isinstance(images, (list, )):
             images = [images]
         for idx in range(len(images)):
             for ops in self.preprocess_ops:
                 images[idx] = ops(images[idx])
         image = np.array(images)
+        if self.benchmark:
+            self.auto_logger.times.stamp()
 
         input_tensor.copy_from_cpu(image)
         self.paddle_predictor.run()
         batch_output = output_tensor.copy_to_cpu()
+        if self.benchmark:
+            self.auto_logger.times.stamp()
         if self.postprocess is not None:
             batch_output = self.postprocess(batch_output)
+        if self.benchmark:
+            self.auto_logger.times.end(stamp=True)
         return batch_output
 
 
@@ -83,10 +115,11 @@ def main(config):
             batch_names.append(img_name)
             cnt += 1
 
-        if cnt % config["Global"]["batch_size"] == 0 or (idx + 1) == len(image_list):
-            if len(batch_imgs) == 0: 
+        if cnt % config["Global"]["batch_size"] == 0 or (idx + 1
+                                                         ) == len(image_list):
+            if len(batch_imgs) == 0:
                 continue
-                
+
             batch_results = cls_predictor.predict(batch_imgs)
             for number, result_dict in enumerate(batch_results):
                 filename = batch_names[number]
@@ -98,8 +131,11 @@ def main(config):
                       format(filename, clas_ids, scores_str, label_names))
             batch_imgs = []
             batch_names = []
+    if cls_predictor.benchmark:
+        cls_predictor.auto_logger.report()
     return
 
+
 if __name__ == "__main__":
     args = config.parse_args()
     config = config.get_config(args.config, overrides=args.override, show=True)

deploy/utils/predictor.py

@@ -28,7 +28,7 @@ class Predictor(object):
         if args.use_fp16 is True:
             assert args.use_tensorrt is True
         self.args = args
-        self.paddle_predictor = self.create_paddle_predictor(
+        self.paddle_predictor, self.config = self.create_paddle_predictor(
             args, inference_model_dir)
 
     def predict(self, image):
@@ -59,11 +59,12 @@ class Predictor(object):
             config.enable_tensorrt_engine(
                 precision_mode=Config.Precision.Half
                 if args.use_fp16 else Config.Precision.Float32,
-                max_batch_size=args.batch_size)
+                max_batch_size=args.batch_size,
+                min_subgraph_size=30)
 
         config.enable_memory_optim()
         # use zero copy
         config.switch_use_feed_fetch_ops(False)
         predictor = create_predictor(config)
 
-        return predictor
+        return predictor, config

tests/DarkNet53.txt

+===========================train_params===========================
+model_name:DarkNet53
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/DarkNet/DarkNet53.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/DarkNet/DarkNet53.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DarkNet/DarkNet53.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+infer_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/DarkNet53_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/HRNet_W18_C.txt

+===========================train_params===========================
+model_name:HRNet_W18_C
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W18_C.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W18_C.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W18_C.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/HRNet_W18_C_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/LeViT_128S.txt

+===========================train_params===========================
+model_name:LeViT_128S
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/LeViT/LeViT_128S.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/LeViT/LeViT_128S.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/LeViT/LeViT_128S.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+infer_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/LeViT_128S_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|Fasle
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/MobileNetV1.txt

+===========================train_params===========================
+model_name:MobileNetV1
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/MobileNetV1_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/MobileNetV2.txt

+===========================train_params===========================
+model_name:MobileNetV2
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+infer_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/MobileNetV2_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/MobileNetV3_large_x1_0.txt

+===========================train_params===========================
+model_name:MobileNetV3_large_x1_0
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml
+pact_train:deploy/slim/slim.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantization.yaml
+fpgm_train:deploy/slim/slim.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml
+quant_export:deploy/slim/slim.py -m export -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantalization.yaml
+fpgm_export:deploy/slim/slim.py -m export -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml
+distill_export:null
+export1:null
+export2:null
+inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/MobileNetV3_large_x1_0_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/ResNeXt101_vd_64x4d.txt

+===========================train_params===========================
+model_name:ResNeXt101_vd_64x4d
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_64x4d.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_64x4d.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_64x4d.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/ResNeXt101_64x4d_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/ResNet50_vd.txt

+===========================train_params===========================
+model_name:ResNet50_vd
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml
+pact_train:deploy/slim/slim.py -c ppcls/configs/slim/ResNet50_vd_quantization.yaml
+fpgm_train:deploy/slim/slim.py -c ppcls/configs/slim/ResNet50_vd_prune.yaml
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml
+quant_export:deploy/slim/slim.py -m export -c ppcls/configs/slim/ResNet50_vd_quantalization.yaml
+fpgm_export:deploy/slim/slim.py -m export -c ppcls/configs/slim/ResNet50_vd_prune.yaml
+distill_export:null
+export1:null
+export2:null
+infer_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/ResNet50_vd_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/ShuffleNetV2_x1_0.txt

+===========================train_params===========================
+model_name:ShuffleNetV2_x1_0
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_0.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_0.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_0.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/ShuffleNetV2_x1_0_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/SwinTransformer_tiny_patch4_window7_224.txt

+===========================train_params===========================
+model_name:SwinTransformer_tiny_patch4_window7_224
+python:python3.7
+gpu_list:0|0,1
+-o Global.device:gpu
+-o Global.auto_cast:null
+-o Global.epochs:lite_train_infer=2|whole_train_infer=120
+-o Global.output_dir:./output/
+-o DataLoader.Train.sampler.batch_size:8
+-o Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./dataset/ILSVRC2012/val
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml
+null:null
+##
+===========================infer_params==========================
+-o Global.save_inference_dir:./inference
+-o Global.pretrained_model:
+norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/SwinTransformer_tiny_patch4_window7_224_inference.tar
+infer_model:../inference/
+infer_export:null
+infer_quant:Fasle
+inference:python/predict_cls.py -c configs/inference_cls.yaml
+-o Global.use_gpu:True|False
+-o Global.enable_mkldnn:True|False
+-o Global.cpu_num_threads:1|6
+-o Global.batch_size:1
+-o Global.use_tensorrt:True|False
+-o Global.use_fp16:True|False
+-o Global.inference_model_dir:../inference
+-o Global.infer_imgs:../dataset/ILSVRC2012/val
+-o Global.save_log_path:null
+-o Global.benchmark:True
+null:null

tests/prepare.sh

+#!/bin/bash
+FILENAME=$1
+# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
+MODE=$2
+
+dataline=$(cat ${FILENAME})
+# parser params
+IFS=$'\n'
+lines=(${dataline})
+function func_parser_value(){
+    strs=$1
+    IFS=":"
+    array=(${strs})
+    if [ ${#array[*]} = 2 ]; then
+        echo ${array[1]}
+    else
+    	IFS="|"
+    	tmp="${array[1]}:${array[2]}"
+        echo ${tmp}
+    fi
+}
+model_name=$(func_parser_value "${lines[1]}")
+inference_model_url=$(func_parser_value "${lines[35]}")
+
+if [ ${MODE} = "lite_train_infer" ] || [ ${MODE} = "whole_infer" ];then
+    # pretrain lite train data
+    cd dataset
+    rm -rf ILSVRC2012
+    wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/whole_chain_little_train.tar
+    tar xf whole_chain_little_train.tar
+    ln -s whole_chain_little_train ILSVRC2012
+    cd ILSVRC2012 
+    mv train.txt train_list.txt
+    mv val.txt val_list.txt
+    cd ../../
+elif [ ${MODE} = "infer" ];then
+    # download data
+    cd dataset
+    rm -rf ILSVRC2012
+    wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/whole_chain_infer.tar
+    tar xf whole_chain_infer.tar
+    ln -s whole_chain_infer ILSVRC2012
+    cd ILSVRC2012 
+    mv val.txt val_list.txt
+    cd ../../
+    # download inference model
+    eval "wget -nc $inference_model_url"
+    tar xf "${model_name}_inference.tar"
+
+elif [ ${MODE} = "whole_train_infer" ];then
+    cd dataset
+    rm -rf ILSVRC2012
+    wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/whole_chain_CIFAR100.tar
+    tar xf whole_chain_CIFAR100.tar
+    ln -s whole_chain_CIFAR100 ILSVRC2012
+    cd ILSVRC2012 
+    mv train.txt train_list.txt
+    mv val.txt val_list.txt
+    cd ../../
+fi

tests/test.sh

+#!/bin/bash
+FILENAME=$1
+# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer'] 
+MODE=$2
+
+dataline=$(cat ${FILENAME})
+
+# parser params
+IFS=$'\n'
+lines=(${dataline})
+
+function func_parser_key(){
+    strs=$1
+    IFS=":"
+    array=(${strs})
+    tmp=${array[0]}
+    echo ${tmp}
+}
+function func_parser_value(){
+    strs=$1
+    IFS=":"
+    array=(${strs})
+    tmp=${array[1]}
+    echo ${tmp}
+}
+function func_set_params(){
+    key=$1
+    value=$2
+    if [ ${key} = "null" ];then
+        echo " "
+    elif [[ ${value} = "null" ]] || [[ ${value} = " " ]] || [ ${#value} -le 0 ];then
+        echo " "
+    else 
+        echo "${key}=${value}"
+    fi
+}
+function func_parser_params(){
+    strs=$1
+    IFS=":"
+    array=(${strs})
+    key=${array[0]}
+    tmp=${array[1]}
+    IFS="|"
+    res=""
+    for _params in ${tmp[*]}; do
+        IFS="="
+        array=(${_params})
+        mode=${array[0]}
+        value=${array[1]}
+        if [[ ${mode} = ${MODE} ]]; then
+            IFS="|"
+            #echo $(func_set_params "${mode}" "${value}")
+            echo $value
+            break
+        fi
+        IFS="|"
+    done
+    echo ${res}
+}
+function status_check(){
+    last_status=$1   # the exit code
+    run_command=$2
+    run_log=$3
+    if [ $last_status -eq 0 ]; then
+        echo -e "\033[33m Run successfully with command - ${run_command}!  \033[0m" | tee -a ${run_log}
+    else
+        echo -e "\033[33m Run failed with command - ${run_command}!  \033[0m" | tee -a ${run_log}
+    fi
+}
+
+IFS=$'\n'
+# The training params
+model_name=$(func_parser_value "${lines[1]}")
+python=$(func_parser_value "${lines[2]}")
+gpu_list=$(func_parser_value "${lines[3]}")
+train_use_gpu_key=$(func_parser_key "${lines[4]}")
+train_use_gpu_value=$(func_parser_value "${lines[4]}")
+autocast_list=$(func_parser_value "${lines[5]}")
+autocast_key=$(func_parser_key "${lines[5]}")
+epoch_key=$(func_parser_key "${lines[6]}")
+epoch_num=$(func_parser_params "${lines[6]}")
+save_model_key=$(func_parser_key "${lines[7]}")
+train_batch_key=$(func_parser_key "${lines[8]}")
+train_batch_value=$(func_parser_params "${lines[8]}")
+pretrain_model_key=$(func_parser_key "${lines[9]}")
+pretrain_model_value=$(func_parser_value "${lines[9]}")
+train_model_name=$(func_parser_value "${lines[10]}")
+train_infer_img_dir=$(func_parser_value "${lines[11]}")
+train_param_key1=$(func_parser_key "${lines[12]}")
+train_param_value1=$(func_parser_value "${lines[12]}")
+
+trainer_list=$(func_parser_value "${lines[14]}")
+trainer_norm=$(func_parser_key "${lines[15]}")
+norm_trainer=$(func_parser_value "${lines[15]}")
+pact_key=$(func_parser_key "${lines[16]}")
+pact_trainer=$(func_parser_value "${lines[16]}")
+fpgm_key=$(func_parser_key "${lines[17]}")
+fpgm_trainer=$(func_parser_value "${lines[17]}")
+distill_key=$(func_parser_key "${lines[18]}")
+distill_trainer=$(func_parser_value "${lines[18]}")
+trainer_key1=$(func_parser_key "${lines[19]}")
+trainer_value1=$(func_parser_value "${lines[19]}")
+trainer_key2=$(func_parser_key "${lines[20]}")
+trainer_value2=$(func_parser_value "${lines[20]}")
+
+eval_py=$(func_parser_value "${lines[23]}")
+eval_key1=$(func_parser_key "${lines[24]}")
+eval_value1=$(func_parser_value "${lines[24]}")
+
+save_infer_key=$(func_parser_key "${lines[27]}")
+export_weight=$(func_parser_key "${lines[28]}")
+norm_export=$(func_parser_value "${lines[29]}")
+pact_export=$(func_parser_value "${lines[30]}")
+fpgm_export=$(func_parser_value "${lines[31]}")
+distill_export=$(func_parser_value "${lines[32]}")
+export_key1=$(func_parser_key "${lines[33]}")
+export_value1=$(func_parser_value "${lines[33]}")
+export_key2=$(func_parser_key "${lines[34]}")
+export_value2=$(func_parser_value "${lines[34]}")
+
+# parser inference model 
+infer_model_dir_list=$(func_parser_value "${lines[36]}")
+infer_export_list=$(func_parser_value "${lines[37]}")
+infer_is_quant=$(func_parser_value "${lines[38]}")
+# parser inference 
+inference_py=$(func_parser_value "${lines[39]}")
+use_gpu_key=$(func_parser_key "${lines[40]}")
+use_gpu_list=$(func_parser_value "${lines[40]}")
+use_mkldnn_key=$(func_parser_key "${lines[41]}")
+use_mkldnn_list=$(func_parser_value "${lines[41]}")
+cpu_threads_key=$(func_parser_key "${lines[42]}")
+cpu_threads_list=$(func_parser_value "${lines[42]}")
+batch_size_key=$(func_parser_key "${lines[43]}")
+batch_size_list=$(func_parser_value "${lines[43]}")
+use_trt_key=$(func_parser_key "${lines[44]}")
+use_trt_list=$(func_parser_value "${lines[44]}")
+precision_key=$(func_parser_key "${lines[45]}")
+precision_list=$(func_parser_value "${lines[45]}")
+infer_model_key=$(func_parser_key "${lines[46]}")
+image_dir_key=$(func_parser_key "${lines[47]}")
+infer_img_dir=$(func_parser_value "${lines[47]}")
+save_log_key=$(func_parser_key "${lines[48]}")
+benchmark_key=$(func_parser_key "${lines[49]}")
+benchmark_value=$(func_parser_value "${lines[49]}")
+infer_key1=$(func_parser_key "${lines[50]}")
+infer_value1=$(func_parser_value "${lines[50]}")
+
+LOG_PATH="./tests/output"
+mkdir -p ${LOG_PATH}
+status_log="${LOG_PATH}/results.log"
+
+
+function func_inference(){
+    IFS='|'
+    _python=$1
+    _script=$2
+    _model_dir=$3
+    _log_path=$4
+    _img_dir=$5
+    _flag_quant=$6
+    # inference 
+    for use_gpu in ${use_gpu_list[*]}; do
+        if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then
+            for use_mkldnn in ${use_mkldnn_list[*]}; do
+                if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then
+                    continue
+                fi
+                for threads in ${cpu_threads_list[*]}; do
+                    for batch_size in ${batch_size_list[*]}; do
+                        _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log"
+                        set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
+                        set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
+                        set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
+                        set_cpu_threads=$(func_set_params "${cpu_threads_key}" "${threads}")
+                        set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
+                        set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}")
+                        command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} ${set_infer_params1} > ${_save_log_path} 2>&1 "
+                        eval $command
+                        last_status=${PIPESTATUS[0]}
+                        eval "cat ${_save_log_path}"
+                        status_check $last_status "${command}" "../${status_log}"
+                    done
+                done
+            done
+        elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then
+            for use_trt in ${use_trt_list[*]}; do
+                for precision in ${precision_list[*]}; do
+                    if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
+                        continue
+                    fi
+                    if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then
+                        continue
+                    fi
+                    for batch_size in ${batch_size_list[*]}; do
+                        _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
+                        set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
+                        set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
+                        set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
+                        set_tensorrt=$(func_set_params "${use_trt_key}" "${use_trt}")
+                        set_precision=$(func_set_params "${precision_key}" "${precision}")
+                        set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
+                        command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} > ${_save_log_path} 2>&1 "
+                        eval $command
+                        last_status=${PIPESTATUS[0]}
+                        eval "cat ${_save_log_path}"
+                        status_check $last_status "${command}" "../${status_log}"
+                        
+                    done
+                done
+            done
+        else
+            echo "Does not support hardware other than CPU and GPU Currently!"
+        fi
+    done
+}
+
+if [ ${MODE} = "infer" ]; then
+    GPUID=$3
+    if [ ${#GPUID} -le 0 ];then
+        env=" "
+    else
+        env="export CUDA_VISIBLE_DEVICES=${GPUID}"
+    fi
+    # set CUDA_VISIBLE_DEVICES
+    eval $env
+    export Count=0
+    IFS="|"
+    infer_run_exports=(${infer_export_list})
+    infer_quant_flag=(${infer_is_quant})
+    cd deploy
+    for infer_model in ${infer_model_dir_list[*]}; do
+        # run export
+        if [ ${infer_run_exports[Count]} != "null" ];then
+            set_export_weight=$(func_set_params "${export_weight}" "${infer_model}")
+            set_save_infer_key=$(func_set_params "${save_infer_key}" "${infer_model}")
+            export_cmd="${python} ${norm_export} ${set_export_weight} ${set_save_infer_key}"
+            eval $export_cmd
+            status_export=$?
+            if [ ${status_export} = 0 ];then
+                status_check $status_export "${export_cmd}" "../${status_log}"
+            fi
+        fi
+        #run inference
+        is_quant=${infer_quant_flag[Count]}
+        echo "is_quant: ${is_quant}"
+        func_inference "${python}" "${inference_py}" "${infer_model}" "../${LOG_PATH}" "${infer_img_dir}" ${is_quant}
+        Count=$(($Count + 1))
+    done
+    cd ..
+
+else
+    IFS="|"
+    export Count=0
+    USE_GPU_KEY=(${train_use_gpu_value})
+    for gpu in ${gpu_list[*]}; do
+        use_gpu=${USE_GPU_KEY[Count]}
+        Count=$(($Count + 1))
+        if [ ${gpu} = "-1" ];then
+            env=""
+        elif [ ${#gpu} -le 1 ];then
+            env="export CUDA_VISIBLE_DEVICES=${gpu}"
+            eval ${env}
+        elif [ ${#gpu} -le 15 ];then
+            IFS=","
+            array=(${gpu})
+            env="export CUDA_VISIBLE_DEVICES=${array[0]}"
+            IFS="|"
+        else
+            IFS=";"
+            array=(${gpu})
+            ips=${array[0]}
+            gpu=${array[1]}
+            IFS="|"
+            env=" "
+        fi
+        for autocast in ${autocast_list[*]}; do 
+            for trainer in ${trainer_list[*]}; do 
+                flag_quant=False
+                if [ ${trainer} = ${pact_key} ]; then
+                    run_train=${pact_trainer}
+                    run_export=${pact_export}
+                    flag_quant=True
+                elif [ ${trainer} = "${fpgm_key}" ]; then
+                    run_train=${fpgm_trainer}
+                    run_export=${fpgm_export}
+                elif [ ${trainer} = "${distill_key}" ]; then
+                    run_train=${distill_trainer}
+                    run_export=${distill_export}
+                elif [ ${trainer} = ${trainer_key1} ]; then
+                    run_train=${trainer_value1}
+                    run_export=${export_value1}
+                elif [[ ${trainer} = ${trainer_key2} ]]; then
+                    run_train=${trainer_value2}
+                    run_export=${export_value2}
+                else
+                    run_train=${norm_trainer}
+                    run_export=${norm_export}
+                fi
+
+                if [ ${run_train} = "null" ]; then
+                    continue
+                fi
+                
+                set_autocast=$(func_set_params "${autocast_key}" "${autocast}")
+                set_epoch=$(func_set_params "${epoch_key}" "${epoch_num}")
+                set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}")
+                set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}")
+                set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}")
+                set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${use_gpu}")
+                save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
+                
+                # load pretrain from norm training if current trainer is pact or fpgm trainer
+                if [ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]; then
+                    set_pretrain="${load_norm_train_model}"
+                fi
+
+                set_save_model=$(func_set_params "${save_model_key}" "${save_log}")
+                if [ ${#gpu} -le 2 ];then  # train with cpu or single gpu
+                    cmd="${python} ${run_train} ${set_use_gpu}  ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} "
+                elif [ ${#gpu} -le 15 ];then  # train with multi-gpu
+                    cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1}"
+                else     # train with multi-machine
+                    cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1}"
+                fi
+                # run train
+		eval "unset CUDA_VISIBLE_DEVICES"
+                eval $cmd
+                status_check $? "${cmd}" "${status_log}"
+
+                set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${$model_name}/${train_model_name}")
+                # save norm trained models to set pretrain for pact training and fpgm training 
+                if [ ${trainer} = ${trainer_norm} ]; then
+                    load_norm_train_model=${set_eval_pretrain}
+                fi
+                # run eval 
+                if [ ${eval_py} != "null" ]; then
+                    set_eval_params1=$(func_set_params "${eval_key1}" "${eval_value1}")
+                    eval_cmd="${python} ${eval_py} ${set_eval_pretrain} ${set_use_gpu} ${set_eval_params1}" 
+                    eval $eval_cmd
+                    status_check $? "${eval_cmd}" "${status_log}"
+                fi
+                # run export model
+                if [ ${run_export} != "null" ]; then 
+                    # run export model
+                    save_infer_path="${save_log}"
+                    set_export_weight=$(func_set_params "${export_weight}" "${save_log}/${model_name}/${train_model_name}")
+                    set_save_infer_key=$(func_set_params "${save_infer_key}" "${save_infer_path}")
+                    export_cmd="${python} ${run_export} ${set_export_weight} ${set_save_infer_key}"
+                    eval $export_cmd
+                    status_check $? "${export_cmd}" "${status_log}"
+
+                    #run inference
+                    eval $env
+                    save_infer_path="${save_log}"
+		    cd deploy
+                    func_inference "${python}" "${inference_py}" "../${save_infer_path}" "../${LOG_PATH}" "${infer_img_dir}" "${flag_quant}"
+		    cd ..
+                fi
+                eval "unset CUDA_VISIBLE_DEVICES"
+            done  # done with:    for trainer in ${trainer_list[*]}; do 
+        done      # done with:    for autocast in ${autocast_list[*]}; do 
+    done          # done with:    for gpu in ${gpu_list[*]}; do
+fi  # end if [ ${MODE} = "infer" ]; then