SNPE SDK inference classification precision is measured against several popular public models. Based on our measurement, the accuracy score do not vary per chipset.
Qualcomm classification precision metrics
The following clasification precision scores are computed by comparing the SNPE inference result with the ground truth:

mAP: mean average presion

Top1 error rate: chance the highestprobability predicted class is not the real class

Top5 error rate: chance the real class is not contained in the 5 classed with highest probablity
Mean Average Precision Calculation
mAP (mean Average Precision) is the Average Precision across all categories. Each AveP (Average Precision) is calculated by:
Where:

k is the rank in the sequence of retrieved documents

n is the number of retrieved documents

P(k) is the precision at cutoff k in the list. The precision is calculated by tp/(tp+fp) where tp is true positives, fp is false positives.

rel(k) is an indicator function equaling 1 if the item at rank k is a relevant document, zero otherwise.

the precision score is zero if no relevant documents get retrieved.
python code example to calculate AP:
for j in range(len(img_sorted)):
if img_sorted[j] in anno_imgs:
count += 1.0
AP += count/rank
rank += 1.0
if (count == 0):
AP = 0
else:
AP = AP/count