What does model.eval() do in pytorch? <a href="https://stackoverflow.com/questions

torch.permute() <div class="snippet-clipboard-content notranslate position-relat

propagate tensor with repeat() <div class="snippet-clipboard-content notranslate

train, evaluate about yolov1 HOT 4 CLOSED

jl749 commented on May 20, 2024

train, evaluate

from yolov1.

Comments (4)

jl749 commented on May 20, 2024

What does model.eval() do in pytorch?
https://stackoverflow.com/questions/60018578/what-does-model-eval-do-in-pytorch

evaluate model:

model.eval()

with torch.no_grad():
    ...
    out_data = model(data)
    ...

training step:

...
model.train()
...

from yolov1.

jl749 commented on May 20, 2024

(7, 7, 30) -- torch.Tensor::unsqueeze(0) --> (1, 7, 7, 30)
(1, 7, 7) -- torch.Tensor::unsqueeze(-1) --> (1, 7, 7, 1)

from yolov1.

jl749 commented on May 20, 2024

torch.permute()

>>> x = torch.randn(2, 3, 5)
>>> x.size()
torch.Size([2, 3, 5])
>>> torch.permute(x, (2, 0, 1)).size()
torch.Size([5, 2, 3])\

from yolov1.

jl749 commented on May 20, 2024

propagate tensor with repeat()

batch size = 1
cell_indices = torch.arange(S).repeat(batch_size, S, 1).unsqueeze(-1)  # (1, 7, 7, 1)

result tensor

tensor([[[[0],
          [1],
          [2],
          [3],
          [4],
          [5],
          [6]],

         [[0],
          [1],
          [2],
          [3],
          [4],
          [5],
          [6]],

         [[0],
          [1],
          [2],
          [3],
          [4],
          [5],
          [6]],

         [[0],
          [1],
          [2],
          [3],
          [4],
          [5],
          [6]],

         [[0],
          [1],
          [2],
          [3],
          [4],
          [5],
          [6]],

         [[0],
          [1],
          [2],
          [3],
          [4],
          [5],
          [6]],

         [[0],
          [1],
          [2],
          [3],
          [4],
          [5],
          [6]]]])

swap 1st 2nd indexes

cell_indices.permute(0, 2, 1, 3))

result tensor

tensor([[[[0],
          [0],
          [0],
          [0],
          [0],
          [0],
          [0]],

         [[1],
          [1],
          [1],
          [1],
          [1],
          [1],
          [1]],

         [[2],
          [2],
          [2],
          [2],
          [2],
          [2],
          [2]],

         [[3],
          [3],
          [3],
          [3],
          [3],
          [3],
          [3]],

         [[4],
          [4],
          [4],
          [4],
          [4],
          [4],
          [4]],

         [[5],
          [5],
          [5],
          [5],
          [5],
          [5],
          [5]],

         [[6],
          [6],
          [6],
          [6],
          [6],
          [6],
          [6]]]])

from yolov1.

Recommend Projects