paddlemix add deploy benchmark (#633) (#636)

Author: LokeZhou

deploy/README.md

@@ -74,3 +74,17 @@ python export.py \
  --prompt "bus"
 
 ```
+
+## 3. 推理 BenchMark
+
+> Note: 
+> 测试环境为Paddle 3.0，A100 80G单卡。
+
+# A100性能数据
+|模型|Paddle Deploy |
+|-|-|
+|qwen-vl-7b|669.8 ms|
+|llava-1.5-7b|981.2 ms|
+|llava-1.6-7b|778.7 ms|
+|groundingDino/groundingdino-swint-ogc|100 ms|
+|Sam/SamVitH-1024|121 ms|

deploy/README_en.md

@@ -74,3 +74,16 @@ Will be exported to the following directory, including `model_state.pdiparams`,
 
 ```
 
+## 3. BenchMark
+
+> Note: 
+> Paddle 3.0，A100 80G。
+
+
+|Model|Paddle Deploy |
+|-|-|
+|qwen-vl-7b|669.8 ms|
+|llava-1.5-7b|981.2 ms|
+|llava-1.6-7b|778.7 ms|
+|groundingDino/groundingdino-swint-ogc|100 ms|
+|Sam/SamVitH-1024|121 ms|

deploy/groundingdino/predict.py

@@ -229,6 +229,19 @@ def main(model_args, data_args):
         image_pil = Image.open(data_args.input_image).convert("RGB")
     else:
         image_pil = Image.open(requests.get(url, stream=True).raw).convert("RGB")
+    
+    if model_args.benchmark:
+        import time
+        start = 0.0
+        total = 0.0
+        for i in range(20):
+            if i>10:
+                start = time.time()
+            boxes_filt, pred_phrases = predictor.run(image_pil, data_args.prompt)
+            if i > 10:
+                total += time.time()-start
+
+        print("Time:",total/10)
 
     boxes_filt, pred_phrases = predictor.run(image_pil, data_args.prompt)
 
@@ -294,6 +307,10 @@ class ModelArguments:
         default="GPU",
         metadata={"help": "Choose the device you want to run, it can be: CPU/GPU/XPU, default is CPU."},
     )
+    benchmark: bool = field(
+        default=False,
+        metadata={"help": "benchmark"}
+    )
 
 
 if __name__ == "__main__":

deploy/sam/predict.py

@@ -295,6 +295,10 @@ class ModelArguments:
         default=True,
         metadata={"help": "save visual image."},
     )
+    benchmark: bool = field(
+        default=False,
+        metadata={"help": "benchmark"}
+    )
 
 
 def main(model_args, data_args):
@@ -317,6 +321,19 @@ def main(model_args, data_args):
         auto_tune(model_args, [image_pil], tune_img_nums)
 
     predictor = Predictor(model_args)
+    
+    if model_args.benchmark:
+        import time
+        start = 0.0
+        total = 0.0
+        for i in range(20):
+            if i>10:
+                start = time.time()
+            seg_masks = predictor.run(image_pil, {"points": data_args.points_prompt, "boxs": data_args.box_prompt})
+            if i > 10:
+                total += time.time()-start
+
+        print("Time:",total/10)
 
     seg_masks = predictor.run(image_pil, {"points": data_args.points_prompt, "boxs": data_args.box_prompt})