add CPU checks

handler.py

@@ -9,6 +9,8 @@ from utils import MultiHeadModel, BertInputBuilder, get_num_words
 
 import transformers
 from transformers import BertTokenizer, BertForSequenceClassification
+import psutil
+import time
 
 
 transformers.logging.set_verbosity_debug()
@@ -241,21 +243,34 @@ class EndpointHandler():
             transcript.add_utterance(Utterance(**utt))
 
         print("Running inference on %d examples..." % transcript.length())
-
+        cpu_percent = psutil.cpu_percent()
+        print(f"CPU Usage before models loaded: {cpu_percent}%")
         # Uptake
         uptake_model = UptakeModel(
             self.device, self.tokenizer, self.input_builder)
         uptake_model.run_inference(transcript, min_prev_words=params['uptake_min_num_words'],
                                    uptake_speaker=params.pop("uptake_speaker", None))
+        cpu_percent = psutil.cpu_percent()
+        print(f"CPU Usage after model 1 loaded: {cpu_percent}%")
         del uptake_model
+        cpu_percent = psutil.cpu_percent()
+        print(f"CPU Usage after model 1 deleted: {cpu_percent}%")
         # Reasoning
         reasoning_model = ReasoningModel(
             self.device, self.tokenizer, self.input_builder)
         reasoning_model.run_inference(transcript)
+        cpu_percent = psutil.cpu_percent()
+        print(f"CPU Usage after model 2 loaded: {cpu_percent}%")
         del reasoning_model
+        cpu_percent = psutil.cpu_percent()
+        print(f"CPU Usage after model 2 deleted: {cpu_percent}%")
         # Question
         question_model = QuestionModel(
             self.device, self.tokenizer, self.input_builder)
         question_model.run_inference(transcript)
+        cpu_percent = psutil.cpu_percent()
+        print(f"CPU Usage after model 3 loaded: {cpu_percent}%")
         del question_model
+        cpu_percent = psutil.cpu_percent()
+        print(f"CPU Usage after model 3 deleted: {cpu_percent}%")
         return transcript.to_dict()