Error in JpegCompression

[yingqichao]

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 1, 256, 256]], which is output 0 of UnsqueezeBackward1, is at version 3; expected version 2 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

[reliarui]

In def apply_conv, "image_conv = F.conv2d(image_yuv_ch, filters, stride=8)“ -》 "image_conv = F.conv2d(image_yuv_ch**.clone()**, filters, stride=8)"