change compound_coef, mismatch of the number of layers

[wxzb625]

return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [64, 32, 3, 3], expected input[2, 24, 98, 162] to have 32 channels, but got 24 channels instead

Thank you for your excellent work, when I changed compound_coef=3 to compound_coef=1, why do I get the above error, why do I get the error of mismatch of the number of layers, I hope to get your answer.