insightface
insightface copied to clipboard
deepinsight
mobileface test in MFR
用arcface_torch训练好的mobileface测试MFR的表现时，提示： Non-zero status code returned while running MatMul node. Name:'MatMul_177' Status Message: matmul_helper.h:55 Compute MatMul dimension mismatch
请问需要调整网络来做测试吗
做了一下调整可以跑通MFR测试，但是onnx_helper.py会报
2023-03-31 18:13:30.296547356 [W:onnxruntime:, execution_frame.cc:835 VerifyOutputSizes] Expected shape from model of {1,512} does not match actual shape of {32,512} for output 1333
err: max time cost exceed, given 60.1430
这是正常的吗
做了一下调整可以跑通MFR测试，但是onnx_helper.py会报
2023-03-31 18:13:30.296547356 [W:onnxruntime:, execution_frame.cc:835 VerifyOutputSizes] Expected shape from model of {1,512} does not match actual shape of {32,512} for output 1333 err: max time cost exceed, given 60.1430这是正常的吗
请问怎么调整可以跑通MFR测试呀？
做了一下调整可以跑通MFR测试，但是onnx_helper.py会报
2023-03-31 18:13:30.296547356 [W:onnxruntime:, execution_frame.cc:835 VerifyOutputSizes] Expected shape from model of {1,512} does not match actual shape of {32,512} for output 1333 err: max time cost exceed, given 60.1430这是正常的吗
我也遇到这个，这个正常吗？
做了一下调整可以跑通MFR测试，但是onnx_helper.py会报
2023-03-31 18:13:30.296547356 [W:onnxruntime:, execution_frame.cc:835 VerifyOutputSizes] Expected shape from model of {1,512} does not match actual shape of {32,512} for output 1333 err: max time cost exceed, given 60.1430这是正常的吗
请问解决了吗
做了一下调整可以跑通MFR测试，但是onnx_helper.py会报
2023-03-31 18:13:30.296547356 [W:onnxruntime:, execution_frame.cc:835 VerifyOutputSizes] Expected shape from model of {1,512} does not match actual shape of {32,512} for output 1333 err: max time cost exceed, given 60.1430这是正常的吗
请问您怎么调整的 能指导一下吗
做了一下调整可以跑通MFR测试，但是onnx_helper.py会报
2023-03-31 18:13:30.296547356 [W:onnxruntime:, execution_frame.cc:835 VerifyOutputSizes] Expected shape from model of {1,512} does not match actual shape of {32,512} for output 1333 err: max time cost exceed, given 60.1430这是正常的吗
请问怎么调整可以跑通MFR测试呀？
有搞定嘛