[autotvm] fix typos in comment (#4591)

python/tvm/autotvm/database.py

@@ -156,7 +156,7 @@ class RedisDatabase(Database):
         Examples
         --------
         get records for a target
-        >>> db.filter(lambda inp, resulst: "cuda" in inp.target.keys)
+        >>> db.filter(lambda inp, results: "cuda" in inp.target.keys)
         get records with errors
         >>> db.filter(lambda inp, results: any(r.error_no != 0 for r in results))
         """

python/tvm/autotvm/tophub.py

@@ -223,7 +223,7 @@ def load_reference_log(backend, model, workload_name, template_key):
                 if model == inp.target.model:
                     find = True
                     break
-            # if device model is not find, use the device model with the most tuned worklaods
+            # if device model is not find, use the device model with the most tuned workloads
             if not find and counts:
                 model = max(counts.items(), key=lambda k: k[1])[0]
 

python/tvm/autotvm/tuner/xgboost_cost_model.py

@@ -51,7 +51,7 @@ class XGBoostCostModel(CostModel):
                                 'itervar' is more accurate but 'knob' is much faster.
                                 There are some constraints on 'itervar', if you meet
                                 problems with feature extraction when using 'itervar',
-                                you can swith to 'knob'.
+                                you can switch to 'knob'.
 
         For cross-shape tuning (e.g. many convolutions with different shapes),
                                'itervar' and 'curve' has better transferability,

python/tvm/autotvm/tuner/xgboost_tuner.py

@@ -40,7 +40,7 @@ class XGBTuner(ModelBasedTuner):
                                 'itervar' is more accurate but 'knob' is much faster.
                                 There are some constraints on 'itervar', if you meet
                                 problems with feature extraction when using 'itervar',
-                                you can swith to 'knob'.
+                                you can switch to 'knob'.
 
         For cross-shape tuning (e.g. many convolutions with different shapes),
                                'itervar' and 'curve' has better transferability,