Lines Matching full:randint
2197 end = torch.randint(1, L, size=()).item()
2638 targets = torch.randint(1, 15, (sum(target_lengths),), dtype=torch.int)
2651 targets = torch.randint(1, 15, (3, 29), dtype=torch.long, device='cuda')
2659 targets = torch.randint(1, 15, (3, 29), dtype=torch.int)
2672 …targets = torch.randint(low=1, high=vocab_size - 1, size=(batch_size, target_length), dtype=torch.…
2695 target = torch.randint(low=1, high=C, size=(S,), dtype=torch.int)
2711 target = torch.randint(low=1, high=C, size=(N, S), dtype=torch.int)
2732 targets = torch.randint(1, 15, (sum(target_lengths),), dtype=torch.int, device='cuda')
4414 upscale_factor = random.randint(2, 5) if upscale_factor is None else upscale_factor
4416 channels = random.randint(1, 4) * upscale_factor ** 2 + (0 if valid_channels_dim else 1)
4417 height = random.randint(5, 10)
4418 width = random.randint(5, 10)
4425 batch_sizes = [random.randint(1, 3) for _ in range(num_input_dims - 3)]
4444 … downscale_factor = random.randint(2, 5) if downscale_factor is None else downscale_factor
4445 channels = random.randint(1, 4)
4447 height = random.randint(3, 5) * abs(downscale_factor) + (0 if valid_height_dim else 1)
4449 width = random.randint(3, 5) * abs(downscale_factor) + (0 if valid_width_dim else 1)
4456 batch_sizes = [random.randint(1, 3) for _ in range(num_input_dims - 3)]
4895 input = torch.randint(1, 10, (4, 8, 2, 2), dtype=torch.float32, device="cuda")
4898 grad = torch.randint(1, 10, (4, 8, 2, 2), dtype=torch.float32, device="cuda")
4903 input = torch.randint(1, 10, (2, 8, 8, 1), dtype=torch.float32, device="cuda")
4905 grad = torch.randint(1, 10, (2, 8, 8, 1), dtype=torch.float32, device="cuda")
4912 … input = torch.randint(1, 10, (2, 3, 2, 2), dtype=torch.half, device="cuda", requires_grad=True)
5319 target = torch.randint(0, 9, (2, 2), device=device, dtype=dtype)
5617 N = random.randint(2, 8)
5618 C = random.randint(2, 8)
5619 IH = random.randint(2, 8)
5620 IW = random.randint(2, 8)
5621 H = random.randint(IH + 1, 12)
5622 W = random.randint(IW + 1, 12)
5626 N = random.randint(2, 8)
5627 C = random.randint(2, 8)
5628 IH = random.randint(2, 8)
5629 IW = random.randint(2, 8)
5630 H = random.randint(2, IH)
5631 W = random.randint(2, IW)
5635 N = random.randint(2, 8)
5636 C = random.randint(2, 8)
5639 H = random.randint(2, 5)
5640 W = random.randint(2, 5)
5644 N = random.randint(2, 8)
5645 C = random.randint(2, 8)
5646 IH = random.randint(2, 8)
5647 IW = random.randint(2, 8)
5648 W = random.randint(3, IW + 2)
5652 N = random.randint(2, 8)
5653 IH = random.randint(2, 8)
5654 IW = random.randint(2, 8)
5655 H = random.randint(3, IH + 2)
5656 W = random.randint(3, IW + 2)
5660 C = random.randint(2, 8)
5661 IH = random.randint(2, 8)
5662 IW = random.randint(2, 8)
5663 H = random.randint(3, IH + 2)
5664 W = random.randint(3, IW + 2)
5872 N = random.randint(2, 8)
5873 C = random.randint(2, 6)
5874 H = random.randint(2, 8)
5875 W = random.randint(2, 8)
5934 N = random.randint(2, 7)
5935 C = random.randint(2, 5)
5936 ID = random.randint(2, 7)
5937 IH = random.randint(2, 7)
5938 IW = random.randint(2, 7)
5939 D = random.randint(ID + 1, 10)
5940 H = random.randint(IH + 1, 10)
5941 W = random.randint(IW + 1, 10)
5945 N = random.randint(2, 7)
5946 C = random.randint(2, 5)
5947 ID = random.randint(2, 7)
5948 IH = random.randint(2, 7)
5949 IW = random.randint(2, 7)
5950 D = random.randint(2, ID)
5951 H = random.randint(2, IH)
5952 W = random.randint(2, IW)
5956 N = random.randint(2, 7)
5957 C = random.randint(2, 7)
5961 H = random.randint(2, 5)
5962 W = random.randint(2, 5)
5966 N = random.randint(2, 7)
5967 C = random.randint(2, 5)
5968 ID = random.randint(2, 7)
5969 IH = random.randint(2, 7)
5970 IW = random.randint(2, 7)
5971 D = random.randint(3, ID + 2)
5972 W = random.randint(3, IW + 2)
5976 N = random.randint(2, 7)
5977 ID = random.randint(2, 5)
5978 IH = random.randint(2, 7)
5979 IW = random.randint(2, 7)
5980 D = random.randint(3, ID + 2)
5981 H = random.randint(3, IH + 2)
5982 W = random.randint(3, IW + 2)
5986 C = random.randint(2, 5)
5987 ID = random.randint(2, 7)
5988 IH = random.randint(2, 7)
5989 IW = random.randint(2, 7)
5990 D = random.randint(3, ID + 2)
5991 H = random.randint(3, IH + 2)
5992 W = random.randint(3, IW + 2)
5999 N = random.randint(2, 5)
6000 C = random.randint(2, 4)
6001 D = random.randint(2, 5)
6002 H = random.randint(2, 5)
6003 W = random.randint(2, 5)
6196 N = random.randint(1, 8)
6197 C = random.randint(1, 8)
6198 H = random.randint(1, 8)
6199 W = random.randint(1, 8)
6210 N = random.randint(1, 8)
6211 C = random.randint(1, 8)
6212 H = random.randint(1, 8)
6213 W = random.randint(1, 8)
6247 N = random.randint(1, 8)
6248 C = random.randint(1, 8)
6249 D = random.randint(1, 8)
6250 H = random.randint(1, 8)
6251 W = random.randint(1, 8)
6262 N = random.randint(1, 8)
6263 C = random.randint(1, 8)
6264 D = random.randint(1, 8)
6265 H = random.randint(1, 8)
6266 W = random.randint(1, 8)
6899 target = torch.randint(2, (128, 768, 768), dtype=torch.long)
7308 return torch.randint(-1000, 1000, size=size).double()
7708 shape = torch.randint(3, 6, (i,), dtype=torch.long).tolist()
7710 normalized_ndim = random.randint(1, i - 1) # inclusive
8256 b = random.randint(3, 5)
8257 c = random.randint(3, 5)
8258 d = random.randint(8, 10)
8267 b = random.randint(3, 5)
8268 c = random.randint(3, 5)
8269 w = random.randint(3, 6)
8270 h = random.randint(6, 8)
8279 b = random.randint(3, 5)
8280 c = random.randint(3, 5)
8281 w = random.randint(2, 5)
8282 h = random.randint(2, 5)
8283 d = random.randint(2, 5)
8864 targets = torch.randint(22, (56,), device=device)
9129 targets = torch.randint(1, 20, (16, 30), dtype=torch.long, device=device)
9131 target_lengths = torch.randint(10, 30, (16,), dtype=torch.long, device=device)
9725 …input_ui8 = torch.randint(*input_range, size=(batch_size, num_channels, 400, 400), dtype=torch.uin…
9785 …input_ui8 = torch.randint(0, 256, size=(1, 3, input_size, input_size), dtype=torch.uint8, device=d…
9912 src_mask_orig = torch.randint(0, 2, (L, L)).bool()
9916 src_key_padding_mask_orig = torch.randint(0, 2, (B, L)).bool()
9920 generic_mask = torch.randint(0, 2, (B, num_heads, L, L)).bool()
9966 src_mask = torch.randint(0, 2, (L, L)).bool()
9968 src_key_padding_mask = torch.randint(0, 2, (B, L)).bool()
9970 generic_mask = torch.randint(0, 2, (B, num_heads, L, L)).bool()
10005 mask = torch.randint(0, 2, (B, L))
10041 mask = torch.randint(0, 2, (B, L))
10089 mask = torch.randint(0, 2, shape).bool()
10115 mask = torch.randint(0, 2, (B, L))
10136 mask = torch.randint(0, 2, (L, L))
10259 x_small = torch.randint(100, shape, dtype=dtype, device=device)
10698 targets = torch.randint(1, 15, (sum(target_lengths),), dtype=torch.int)
10725 targets = torch.randint(low=1, high=vocab_size - 1, size=(batch_size, target_length),
10809 seqs = [torch.empty(random.randint(1, 6), device=device, dtype=dtype)
11154 targets = torch.randint(1, 15, (0,), dtype=torch.long, device=device)
11162 targets = torch.randint(1, 15, (9,), dtype=torch.long, device=device)
11195 targets = torch.randint(1, num_labels, (batch_size, target_length),
11200 input_lengths = [(torch.randint(input_length // 2, input_length + 1, ()).item()
11205 target_lengths = [(torch.randint(target_length // 2, target_length + 1, ()).item()
11208 idxes = torch.randint(0, batch_size, (10,))
11228 targets = torch.randint(1, num_labels, (batch_size * target_length,),
11253 targets = torch.randint(1, num_labels, (batch_size * target_length,),
11494 labels = torch.randint(shape[0], (shape[0],), dtype=torch.long, device=device)
11535 target = torch.randint(num_channels, target_size, device=device)
11668 other_dims = [torch.randint(2, 5, size=(1,)).item() for _ in range(k)]
11684 other_dims = [torch.randint(2, 5, size=(1,)).item() for _ in range(k)]
11715 other_dims = [torch.randint(2, 5, size=(1,)).item() for _ in range(k)]
11732 other_dims = [torch.randint(2, 5, size=(1,)).item() for _ in range(k)]
11776 other_dims = [torch.randint(2, 5, size=(1,)).item() for _ in range(k)]
11810 other_dims = [torch.randint(2, 5, size=(1,)).item() for _ in range(k)]