roseif

What is the reason for this problem during training？

2

Traceback (most recent call last): File "train_dist.py", line 346, in main() File "train_dist.py", line 114, in main mp.spawn(main_worker, nprocs=ngpus_per_node, args=(ngpus_per_node, args)) File "/home/user05/.conda/envs/open-mmlab1/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 171, in spawn while not spawn_context.join():...

请问一下训练集有分验证集出来吗？

5

想知道您划分的比例是多少，因为我按照您的代码运行出来的准确率有点差异。代码中每隔10个迭代次数进行一次测试还是验证？谢谢您的回答。

HBP定义中的代码我有点不理解

1

proj_1 = self.bilinear_proj(conv1) proj_2 = self.bilinear_proj(conv2) assert(proj_1.size() == (N,8192,28,28)) X = proj_1 * proj_2 assert(X.size() == (N,8192,28,28)) 这里不应该是两个卷积层外积操作吗？出来不应该是[N,8192,8192]吗？为什么是(N,8192,784))

rand_h_1 = np.random.randint(output_dim, size=self.input_dim1) and rand_s_1 = 2 * np.random.randint(2, size=self.input_dim1) - 1 in the code seem to be different from the setting of the paper. In the paper, hk...

Training does not converge after joining compact bilinear layer

3

Source code： x = self.features(x) #[4,512,28,28] batch_size = x.size(0) x = (torch.bmm(x, torch.transpose(x, 1, 2)) / 28 ** 2).view(batch_size, -1) x = torch.nn.functional.normalize(torch.sign(x) * torch.sqrt(torch.abs(x) + 1e-10)) x = self.classifiers(x)...