Wrong construction of the first conv layer in R2Plus1D_model.py

[Taylor-X76]

In R2Plus1D_model.py, line 200：

pytorch-video-recognition/network/R2Plus1D_model.py

Line 200 in ca37de9

self.conv1 = SpatioTemporalConv(3, 64, (1, 7, 7), stride=(1, 2, 2), padding=(0, 3, 3), first_conv=True)

It's actually a convolution of 3 * 7 * 7 with padding=(1, 3, 3), not 1 * 7 * 7！