batch = dls %>% one_batch(convert = FALSE)
[[1]]
TensorImage([[[[-1.4419e+00, -1.3117e+00, -1.1976e+00, ..., 2.2489e+00,
2.2238e+00, 2.0948e+00],
[-1.5401e+00, -1.5213e+00, -1.4010e+00, ..., 1.9834e+00,
2.2378e+00, 2.2173e+00],
[-1.6401e+00, -1.5477e+00, -1.5588e+00, ..., 9.1953e-01,
1.9501e+00, 1.1138e+00],
...,
[-1.6852e+00, -1.5440e+00, -1.5132e+00, ..., -1.0596e+00,
-1.0711e+00, -1.0674e+00],
[-1.5265e+00, -1.6030e+00, -1.5804e+00, ..., -1.0268e+00,
-1.0946e+00, -1.1181e+00],
[-1.5423e+00, -1.5516e+00, -1.6014e+00, ..., -1.1734e+00,
-1.1293e+00, -1.0777e+00]],
[[-1.3446e+00, -1.2023e+00, -1.0470e+00, ..., 2.4286e+00,
2.4090e+00, 2.2977e+00],
[-1.4481e+00, -1.4276e+00, -1.2930e+00, ..., 2.1422e+00,
2.4158e+00, 2.3778e+00],
[-1.5607e+00, -1.4584e+00, -1.4641e+00, ..., 1.0026e+00,
2.0258e+00, 1.1376e+00],
...,
[-1.5809e+00, -1.4399e+00, -1.4133e+00, ..., -7.8931e-01,
-7.9807e-01, -7.9637e-01],
[-1.4161e+00, -1.4909e+00, -1.4646e+00, ..., -8.0615e-01,
-8.5201e-01, -8.5311e-01],
[-1.4472e+00, -1.4567e+00, -1.5077e+00, ..., -9.4607e-01,
-8.9744e-01, -8.2074e-01]],
[[-1.1164e+00, -1.0162e+00, -9.1189e-01, ..., 2.6257e+00,
2.5726e+00, 2.4016e+00],
[-1.2195e+00, -1.1752e+00, -1.0595e+00, ..., 2.3488e+00,
2.6271e+00, 2.5764e+00],
[-1.3316e+00, -1.2451e+00, -1.2400e+00, ..., 1.0476e+00,
2.1812e+00, 1.3635e+00],
...,
[-1.2881e+00, -1.1393e+00, -1.1035e+00, ..., -3.8940e-01,
-4.0598e-01, -3.9861e-01],
[-1.1427e+00, -1.2167e+00, -1.1906e+00, ..., -3.6462e-01,
-4.3055e-01, -4.5333e-01],
[-1.1525e+00, -1.1651e+00, -1.2190e+00, ..., -4.8259e-01,
-4.3712e-01, -4.1413e-01]]],
[[[-2.0552e-01, 3.9563e-01, 4.0691e-01, ..., -9.7342e-01,
-7.8957e-01, -7.6035e-01],
[-3.8852e-01, 4.2912e-01, 4.4469e-01, ..., -1.0449e+00,
-8.5347e-01, -7.5299e-01],
[ 3.5939e-01, 3.6353e-01, 4.7028e-01, ..., -9.3101e-01,
-8.7398e-01, -7.9327e-01],
...,
[-1.0510e+00, -1.0661e+00, -9.6690e-01, ..., -1.3688e+00,
-1.4543e+00, -1.4645e+00],
[-1.0578e+00, -1.0939e+00, -9.3117e-01, ..., -1.3939e+00,
-1.4033e+00, -1.4209e+00],
[-9.9012e-01, -1.0312e+00, -1.0074e+00, ..., -1.4274e+00,
-1.3829e+00, -1.3758e+00]],
[[ 6.0090e-02, 7.8124e-01, 7.5145e-01, ..., -8.2881e-01,
-6.7773e-01, -6.3718e-01],
[-1.7114e-01, 7.8613e-01, 7.8531e-01, ..., -9.0003e-01,
-7.3661e-01, -5.8707e-01],
[ 7.3440e-01, 7.5691e-01, 8.2297e-01, ..., -8.0694e-01,
-7.5451e-01, -6.2783e-01],
...,
[-7.8971e-01, -7.8585e-01, -7.4870e-01, ..., -1.2630e+00,
-1.3108e+00, -1.3046e+00],
[-7.8414e-01, -7.9617e-01, -7.2847e-01, ..., -1.2297e+00,
-1.2414e+00, -1.2594e+00],
[-7.3135e-01, -7.7442e-01, -7.4849e-01, ..., -1.2259e+00,
-1.1889e+00, -1.2022e+00]],
[[ 4.4920e-01, 1.2392e+00, 1.3399e+00, ..., -6.0991e-01,
-4.5250e-01, -4.4251e-01],
[ 2.7577e-01, 1.2913e+00, 1.3755e+00, ..., -6.8060e-01,
-5.1114e-01, -3.7442e-01],
[ 1.0632e+00, 1.3052e+00, 1.3774e+00, ..., -5.8343e-01,
-5.2787e-01, -3.9803e-01],
...,
[-4.4165e-01, -4.4558e-01, -3.8942e-01, ..., -8.7048e-01,
-9.2835e-01, -9.2750e-01],
[-4.4233e-01, -4.6348e-01, -3.7176e-01, ..., -8.6960e-01,
-8.8080e-01, -8.9788e-01],
[-3.8967e-01, -4.3118e-01, -3.8587e-01, ..., -8.7933e-01,
-8.4775e-01, -8.5052e-01]]],
[[[ 1.2805e+00, 2.2139e+00, 9.9765e-01, ..., 6.6338e-01,
-4.0192e-01, 2.8007e-01],
[ 1.0171e+00, 1.8849e+00, 1.1654e+00, ..., -1.0001e+00,
1.1788e+00, 2.0717e+00],
[ 2.8709e-01, 1.9494e+00, 2.1978e+00, ..., -6.7389e-01,
3.2762e-01, 4.5549e-01],
...,
[-4.3609e-01, -4.2635e-01, -4.6298e-01, ..., 7.7548e-02,
3.6271e-02, -3.1759e-02],
[-3.7265e-01, -4.3453e-01, -4.4666e-01, ..., -7.5601e-02,
5.3570e-03, -2.9393e-02],
[-3.7581e-01, -4.0105e-01, -4.2908e-01, ..., 8.5172e-03,
-3.3988e-03, -1.8303e-02]],
[[ 1.3276e+00, 2.3720e+00, 1.0603e+00, ..., 8.6043e-01,
-1.1662e-01, 5.2147e-01],
[ 1.0938e+00, 2.0233e+00, 1.2629e+00, ..., -9.1610e-01,
1.3807e+00, 2.2914e+00],
[ 3.8840e-01, 2.1078e+00, 2.3635e+00, ..., -5.8584e-01,
5.2653e-01, 7.8300e-01],
...,
[-3.1636e-01, -3.0640e-01, -3.4385e-01, ..., 1.3784e-01,
9.5460e-02, 2.5607e-02],
[-2.5150e-01, -3.1476e-01, -3.2716e-01, ..., -1.9409e-02,
6.3717e-02, 2.8037e-02],
[-2.5473e-01, -2.8054e-01, -3.0920e-01, ..., 6.6963e-02,
5.4727e-02, 3.9424e-02]],
[[ 1.8118e+00, 2.6126e+00, 1.5284e+00, ..., 1.3408e+00,
3.8263e-01, 9.4347e-01],
[ 1.4345e+00, 2.2263e+00, 1.5055e+00, ..., -4.0407e-01,
1.9165e+00, 2.5325e+00],
[ 6.9120e-01, 2.3214e+00, 2.5724e+00, ..., -5.9273e-02,
7.6707e-01, 9.8036e-01],
...,
[-3.2707e-02, -2.5592e-02, -6.5520e-02, ..., 3.1733e-01,
2.8317e-01, 2.2166e-01],
[ 1.6474e-02, -4.1773e-02, -5.1314e-02, ..., 1.6267e-01,
2.4836e-01, 2.1449e-01],
[ 2.4832e-02, 1.0270e-02, -1.5259e-02, ..., 2.3768e-01,
2.2930e-01, 2.2220e-01]]],
...,
[[[-1.5176e-02, -1.9729e-02, -5.4177e-02, ..., 2.0812e+00,
2.2489e+00, 2.2242e+00],
[-1.0897e-02, 3.5695e-02, 2.3053e-03, ..., 2.1605e+00,
2.0372e+00, 2.1403e+00],
[-2.8262e-02, -3.0313e-02, -3.4347e-02, ..., 2.2136e+00,
2.2489e+00, 1.2613e+00],
...,
[-1.2644e+00, -1.2548e+00, -1.2313e+00, ..., -1.3335e+00,
-1.3230e+00, -1.2787e+00],
[-1.1986e+00, -1.2068e+00, -1.1631e+00, ..., -1.2694e+00,
-1.2973e+00, -1.2696e+00],
[-1.2508e+00, -1.2447e+00, -1.2294e+00, ..., -1.0572e+00,
-1.0660e+00, -1.0694e+00]],
[[ 2.2227e-01, 2.1430e-01, 2.1605e-01, ..., 2.3389e+00,
2.4286e+00, 2.4286e+00],
[ 2.0176e-01, 2.4693e-01, 2.4092e-01, ..., 2.3745e+00,
2.2931e+00, 2.3820e+00],
[ 1.8103e-01, 1.7892e-01, 1.7477e-01, ..., 2.4036e+00,
2.4286e+00, 1.4878e+00],
...,
[-1.0710e+00, -1.0613e+00, -1.0374e+00, ..., -1.2492e+00,
-1.2385e+00, -1.2225e+00],
[-1.0040e+00, -1.0124e+00, -9.6780e-01, ..., -1.1836e+00,
-1.2122e+00, -1.2193e+00],
[-1.0572e+00, -1.0510e+00, -1.0354e+00, ..., -9.5631e-01,
-9.6512e-01, -9.6444e-01]],
[[ 5.4786e-01, 5.5583e-01, 5.3839e-01, ..., 2.5781e+00,
2.6400e+00, 2.6400e+00],
[ 5.3558e-01, 5.8483e-01, 5.6649e-01, ..., 2.5895e+00,
2.5283e+00, 2.6400e+00],
[ 5.2345e-01, 5.2294e-01, 5.1033e-01, ..., 2.6400e+00,
2.6400e+00, 1.7087e+00],
...,
[-8.1354e-01, -8.0387e-01, -7.9721e-01, ..., -1.0014e+00,
-9.9075e-01, -9.5806e-01],
[-7.4687e-01, -7.5518e-01, -7.2870e-01, ..., -9.4173e-01,
-9.6991e-01, -9.5030e-01],
[-7.9981e-01, -7.9358e-01, -7.9630e-01, ..., -7.3474e-01,
-7.4333e-01, -7.3628e-01]]],
[[[ 6.8056e-01, 6.8056e-01, 6.9105e-01, ..., -3.6921e-01,
-3.1641e-01, -3.3400e-01],
[ 6.9991e-01, 7.1771e-01, 6.8056e-01, ..., -3.3319e-01,
-3.4023e-01, -3.8674e-01],
[ 6.9781e-01, 7.1034e-01, 6.9885e-01, ..., -2.9567e-01,
-3.0638e-01, -2.8775e-01],
...,
[-1.4393e+00, -1.4183e+00, -1.4183e+00, ..., -1.3420e+00,
-1.4022e+00, -1.3872e+00],
[-1.4436e+00, -1.4326e+00, -1.4335e+00, ..., -1.3950e+00,
-1.3800e+00, -1.3734e+00],
[-1.4509e+00, -1.4539e+00, -1.4533e+00, ..., -1.3681e+00,
-1.4340e+00, -1.3650e+00]],
[[ 2.0471e+00, 2.0471e+00, 2.0603e+00, ..., -6.5347e-02,
2.6326e-02, 3.4833e-02],
[ 2.0525e+00, 2.0750e+00, 2.0818e+00, ..., -4.7675e-02,
-5.2935e-03, -2.6855e-02],
[ 2.0976e+00, 2.1136e+00, 2.1051e+00, ..., 1.8606e-02,
4.1052e-02, 8.5274e-02],
...,
[-1.2304e+00, -1.2244e+00, -1.2219e+00, ..., -1.2425e+00,
-1.3041e+00, -1.2836e+00],
[-1.2239e+00, -1.2107e+00, -1.2107e+00, ..., -1.2967e+00,
-1.2813e+00, -1.2746e+00],
[-1.2210e+00, -1.2154e+00, -1.2157e+00, ..., -1.2695e+00,
-1.3401e+00, -1.2696e+00]],
[[ 2.6400e+00, 2.6400e+00, 2.6400e+00, ..., 3.4950e-01,
4.4111e-01, 4.1667e-01],
[ 2.6400e+00, 2.6400e+00, 2.6400e+00, ..., 3.3850e-01,
3.8055e-01, 3.7792e-01],
[ 2.6400e+00, 2.6400e+00, 2.6400e+00, ..., 4.4053e-01,
4.5217e-01, 4.8598e-01],
...,
[-8.2900e-01, -8.1651e-01, -8.1498e-01, ..., -9.5577e-01,
-1.0173e+00, -9.9684e-01],
[-8.3432e-01, -8.2192e-01, -8.2227e-01, ..., -1.0234e+00,
-1.0080e+00, -1.0014e+00],
[-8.3237e-01, -8.2912e-01, -8.2936e-01, ..., -1.0039e+00,
-1.0649e+00, -9.9452e-01]]],
[[[ 2.0699e+00, 1.9477e+00, 2.0700e+00, ..., -1.5310e+00,
-1.6490e+00, -1.6860e+00],
[ 1.8292e+00, 2.1599e+00, 1.8882e+00, ..., -1.6536e+00,
-1.6374e+00, -1.6022e+00],
[ 2.0288e+00, 1.7863e+00, 2.0564e+00, ..., -1.6149e+00,
-1.6315e+00, -1.5586e+00],
...,
[-1.4481e+00, -1.3921e+00, -1.4195e+00, ..., -1.5045e+00,
-1.5133e+00, -1.5381e+00],
[-1.4223e+00, -1.3757e+00, -1.3943e+00, ..., -1.5238e+00,
-1.5371e+00, -1.5453e+00],
[-1.4134e+00, -1.4104e+00, -1.4300e+00, ..., -1.5163e+00,
-1.5862e+00, -1.5565e+00]],
[[ 1.5571e+00, 1.4284e+00, 1.8346e+00, ..., -1.4521e+00,
-1.6496e+00, -1.6908e+00],
[ 1.2790e+00, 1.6710e+00, 1.3942e+00, ..., -1.5838e+00,
-1.6467e+00, -1.6069e+00],
[ 1.4661e+00, 1.2568e+00, 1.7123e+00, ..., -1.5898e+00,
-1.6761e+00, -1.6212e+00],
...,
[-1.2567e+00, -1.2393e+00, -1.2457e+00, ..., -1.4077e+00,
-1.4073e+00, -1.4286e+00],
[-1.2191e+00, -1.2129e+00, -1.2214e+00, ..., -1.4193e+00,
-1.4265e+00, -1.4403e+00],
[-1.2213e+00, -1.2350e+00, -1.2495e+00, ..., -1.4075e+00,
-1.4811e+00, -1.4504e+00]],
[[ 1.1398e+00, 1.0327e+00, 1.4135e+00, ..., -1.2147e+00,
-1.4180e+00, -1.4598e+00],
[ 8.6931e-01, 1.2768e+00, 1.0129e+00, ..., -1.3449e+00,
-1.3906e+00, -1.3518e+00],
[ 1.1199e+00, 9.0534e-01, 1.2758e+00, ..., -1.3922e+00,
-1.4662e+00, -1.4051e+00],
...,
[-8.5999e-01, -8.2594e-01, -8.6729e-01, ..., -1.0699e+00,
-1.0976e+00, -1.1388e+00],
[-8.4630e-01, -8.2145e-01, -8.4266e-01, ..., -1.1058e+00,
-1.1325e+00, -1.1478e+00],
[-8.5198e-01, -8.5977e-01, -8.7435e-01, ..., -1.1186e+00,
-1.1739e+00, -1.1579e+00]]]], device='cuda:0')
[[2]]
TensorMask([[[ 4, 4, 4, ..., 4, 4, 4],
[ 4, 4, 4, ..., 4, 4, 4],
[ 4, 4, 4, ..., 4, 4, 4],
...,
[19, 19, 19, ..., 17, 17, 17],
[19, 19, 19, ..., 17, 17, 17],
[19, 19, 19, ..., 17, 17, 17]],
[[ 4, 4, 4, ..., 4, 4, 4],
[ 4, 4, 4, ..., 4, 4, 4],
[ 4, 4, 4, ..., 4, 4, 4],
...,
[17, 17, 17, ..., 17, 17, 17],
[17, 17, 17, ..., 17, 17, 17],
[17, 17, 17, ..., 17, 17, 17]],
[[26, 21, 26, ..., 26, 26, 26],
[26, 21, 26, ..., 26, 26, 26],
[26, 21, 21, ..., 26, 26, 26],
...,
[17, 17, 17, ..., 17, 17, 17],
[17, 17, 17, ..., 17, 17, 17],
[17, 17, 17, ..., 17, 17, 17]],
...,
[[ 4, 4, 4, ..., 26, 26, 26],
[ 4, 4, 4, ..., 26, 26, 26],
[ 4, 4, 4, ..., 26, 26, 26],
...,
[17, 17, 17, ..., 19, 19, 19],
[17, 17, 17, ..., 19, 19, 19],
[17, 17, 17, ..., 19, 19, 19]],
[[21, 21, 21, ..., 4, 4, 4],
[21, 21, 21, ..., 4, 4, 4],
[21, 21, 21, ..., 4, 4, 4],
...,
[17, 17, 17, ..., 19, 19, 19],
[17, 17, 17, ..., 19, 19, 19],
[17, 17, 17, ..., 19, 19, 19]],
[[ 4, 4, 4, ..., 30, 30, 30],
[ 4, 4, 4, ..., 30, 30, 30],
[ 4, 4, 4, ..., 30, 30, 30],
...,
[17, 17, 17, ..., 17, 17, 17],
[17, 17, 17, ..., 17, 17, 17],
[17, 17, 17, ..., 17, 17, 17]]], device='cuda:0')
batch[[1]]$shape;batch[[2]]$shape
torch.Size([8, 3, 200, 266])
torch.Size([8, 200, 266])
input = batch[[1]]
target = batch[[2]]
mask = target != void_code
TensorMask([[[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
...,
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True]],
[[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
...,
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True]],
[[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
...,
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True]],
...,
[[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
...,
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True]],
[[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
...,
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True]],
[[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
...,
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True],
[True, True, True, ..., True, True, True]]], device='cuda:0')
> (input$argmax(dim=1L)[mask] == target[mask])
tensor([False, False, False, ..., False, False, False], device='cuda:0')
> (input$argmax(dim=1L)[mask] == target[mask]) %>%
float()
tensor([0., 0., 0., ..., 0., 0., 0.], device='cuda:0')
> (input$argmax(dim=1L)[mask]==target[mask]) %>%
float() %>% mean()
tensor(0.0011, device='cuda:0')
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4