---> BasePixrayPredictor Predict Using seed: 16957246150951434758 Working with z of shape (1, 256, 16, 16) = 65536 dimensions. Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to models/checkpoints/vgg16-397923af.pth 0%| | 0.00/528M [00:003.18) 0it [00:01, ?it/s]/root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torch/nn/functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. warnings.warn( 0it [00:23, ?it/s] 0it [00:00, ?it/s] iter: 10, loss: 2.77, losses: 0.0104, 0.756, 0.0783, 0.873, 0.0609, 0.878, 0.0609, 0.0485 (-0=>2.767) 0it [00:01, ?it/s] 0it [00:24, ?it/s] 0it [00:00, ?it/s] iter: 20, loss: 2.43, losses: 0.0155, 0.666, 0.081, 0.763, 0.0639, 0.762, 0.0659, 0.0146 (-0=>2.432) 0it [00:01, ?it/s] 0it [00:24, ?it/s] 0it [00:00, ?it/s] iter: 30, loss: 2.31, losses: 0.00711, 0.616, 0.0856, 0.741, 0.0689, 0.713, 0.0695, 0.00561 (-1=>2.287) 0it [00:01, ?it/s] 0it [00:24, ?it/s] 0it [00:00, ?it/s] iter: 40, loss: 2.16, losses: 0.00336, 0.565, 0.0858, 0.699, 0.0717, 0.666, 0.0709, 0.00382 (-1=>2.159) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 50, loss: 2.13, losses: 0.00226, 0.548, 0.0853, 0.689, 0.0728, 0.656, 0.0704, 0.00306 (-2=>2.073) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 60, loss: 2.06, losses: 0.00242, 0.531, 0.0892, 0.67, 0.0729, 0.624, 0.0721, 0.00252 (-0=>2.064) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 70, loss: 2.05, losses: 0.00159, 0.531, 0.0889, 0.654, 0.074, 0.621, 0.0731, 0.00277 (-9=>2.027) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 80, loss: 2.01, losses: 0.00141, 0.486, 0.09, 0.66, 0.0747, 0.618, 0.073, 0.00312 (-3=>1.983) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 90, loss: 2.01, losses: 0.0013, 0.502, 0.0884, 0.658, 0.0733, 0.607, 0.0731, 0.00281 (-1=>1.974) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 100, loss: 1.99, losses: 0.00114, 0.468, 0.0887, 0.668, 0.0736, 0.616, 0.0733, 0.0026 (-4=>1.943) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 110, loss: 1.98, losses: 0.00141, 0.477, 0.0922, 0.662, 0.0734, 0.601, 0.0736, 0.00265 (-2=>1.918) 0it [00:01, ?it/s] 0it [00:25, ?it/s] iter: 120, loss: 1.91, losses: 0.000881, 0.463, 0.0896, 0.63, 0.0755, 0.571, 0.0757, 0.00262 (-0=>1.908) 0it [00:00, ?it/s] 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 130, loss: 1.97, losses: 0.000827, 0.48, 0.0893, 0.653, 0.0746, 0.591, 0.0758, 0.00291 (-10=>1.908) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 140, loss: 1.97, losses: 0.00177, 0.477, 0.0886, 0.658, 0.0718, 0.594, 0.0734, 0.00279 (-20=>1.908) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 150, loss: 1.91, losses: 0.00169, 0.469, 0.0893, 0.631, 0.0734, 0.569, 0.0753, 0.00278 (-8=>1.905) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 160, loss: 1.9, losses: 0.000808, 0.456, 0.0915, 0.631, 0.0735, 0.569, 0.0764, 0.00311 (-6=>1.895) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 170, loss: 1.91, losses: 0.000962, 0.45, 0.0919, 0.639, 0.0735, 0.572, 0.0767, 0.00297 (-16=>1.895) 0it [00:01, ?it/s]Caught SIGTERM, exiting... 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 180, loss: 1.93, losses: 0.00138, 0.463, 0.0918, 0.644, 0.0722, 0.581, 0.0741, 0.00294 (-5=>1.888) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 190, loss: 1.89, losses: 0.00117, 0.459, 0.0879, 0.624, 0.0746, 0.563, 0.0772, 0.00366 (-15=>1.888) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 200, loss: 1.93, losses: 0.0011, 0.452, 0.0908, 0.652, 0.0718, 0.582, 0.0751, 0.00313 (-7=>1.858) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 210, loss: 1.88, losses: 0.00165, 0.463, 0.0899, 0.614, 0.0729, 0.555, 0.076, 0.00292 (-17=>1.858) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 220, loss: 1.89, losses: 0.00129, 0.477, 0.0898, 0.616, 0.0749, 0.552, 0.078, 0.0031 (-27=>1.858) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 230, loss: 1.9, losses: 0.00065, 0.454, 0.0893, 0.635, 0.0728, 0.57, 0.075, 0.00297 (-37=>1.858) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 240, loss: 1.91, losses: 0.000863, 0.467, 0.0898, 0.629, 0.0719, 0.576, 0.0746, 0.00267 (-47=>1.858) 0it [00:01, ?it/s] 0it [00:25, ?it/s] iter: 250, loss: 1.91, losses: 0.000899, 0.479, 0.0903, 0.625, 0.0727, 0.561, 0.0761, 0.00284 (-57=>1.858) 0it [00:00, ?it/s] 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 260, loss: 1.9, losses: 0.00108, 0.481, 0.09, 0.62, 0.0733, 0.559, 0.0756, 0.00306 (-67=>1.858) Dropping learning rate 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 270, loss: 1.84, losses: 0.0012, 0.438, 0.0921, 0.614, 0.0743, 0.539, 0.076, 0.00323 (-0=>1.838) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 280, loss: 1.92, losses: 0.00098, 0.457, 0.0898, 0.641, 0.0713, 0.581, 0.0739, 0.00288 (-2=>1.828) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 290, loss: 1.89, losses: 0.0013, 0.448, 0.0898, 0.631, 0.0711, 0.574, 0.0745, 0.00304 (-12=>1.828) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 300, loss: 1.84, losses: 0.00112, 0.437, 0.0909, 0.608, 0.0728, 0.552, 0.0766, 0.00312 (-22=>1.828) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 310, loss: 1.87, losses: 0.00143, 0.452, 0.0909, 0.615, 0.073, 0.559, 0.0762, 0.00286 (-32=>1.828) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 320, loss: 1.86, losses: 0.0012, 0.469, 0.0893, 0.607, 0.0744, 0.538, 0.0767, 0.00309 (-42=>1.828) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 330, loss: 1.87, losses: 0.000918, 0.435, 0.0924, 0.626, 0.0728, 0.559, 0.0757, 0.00308 (-52=>1.828) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 340, loss: 1.85, losses: 0.00131, 0.434, 0.0909, 0.621, 0.0742, 0.553, 0.0768, 0.00311 (-62=>1.828) 0it [00:01, ?it/s] 0it [00:25, ?it/s] 0it [00:00, ?it/s] iter: 350, finished (-72=>1.828) 0it [00:00, ?it/s] 0it [00:00, ?it/s]