Update unsuper.
This commit is contained in:
Colin
parent
f3690fd47f
commit
385c438c1c
|
|
@ -0,0 +1,5 @@
|
|||
1. 3x3的时候会有重复
|
||||
1. 重复的权重，虽然权重看起来都一样，但是有稍微的不同，不是完全一样
|
||||
2. 3x3太小了导致了样本的信噪比太低，大部分的样本切出来都是0
|
||||
2. 5x5的时候会有网格状重复
|
||||
3. 7x7的时候边框区域问题
|
||||
|
|
@ -30,7 +30,7 @@ test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, s
|
|||
class ConvNet(nn.Module):
|
||||
def __init__(self):
|
||||
super(ConvNet, self).__init__()
|
||||
self.conv1 = nn.Conv2d(1, 8, 5, 1, 0)
|
||||
self.conv1 = nn.Conv2d(1, 8, 3, 1, 0)
|
||||
self.pool = nn.MaxPool2d(2, 2)
|
||||
self.conv2 = nn.Conv2d(8, 1, 5, 1, 0)
|
||||
self.fc1 = nn.Linear(1 * 4 * 4, 10)
|
||||
|
|
@ -43,7 +43,7 @@ class ConvNet(nn.Module):
|
|||
x = self.fc1(x)
|
||||
return x
|
||||
|
||||
def forward_unsuper(self, x):
|
||||
def normal_conv1_weight(self):
|
||||
weight = self.conv1.weight.reshape(self.conv1.weight.shape[0], -1)
|
||||
weight = weight.permute(1, 0)
|
||||
mean = torch.mean(weight, dim=0)
|
||||
|
|
@ -52,31 +52,31 @@ class ConvNet(nn.Module):
|
|||
weight = weight / sum
|
||||
weight = weight.permute(1, 0)
|
||||
weight = weight.reshape(self.conv1.weight.shape)
|
||||
x = torch.conv2d(x, weight)
|
||||
return weight
|
||||
|
||||
def forward_unsuper(self, x):
|
||||
x = torch.conv2d(x, self.normal_conv1_weight(), stride=1)
|
||||
return x
|
||||
|
||||
def printFector(self, x, label, dir=""):
|
||||
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]), dir + "/input_image.png", Contrast=[0, 1.0])
|
||||
# show.DumpTensorToLog(x, "input_image.log")
|
||||
x = self.conv1(x)
|
||||
w = self.conv1.weight
|
||||
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]), dir + "/conv1_weight.png", Contrast=[-1.0, 1.0])
|
||||
|
||||
w = self.normal_conv1_weight()
|
||||
x = torch.conv2d(x, w)
|
||||
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]), dir + "/conv1_weight.png")
|
||||
# show.DumpTensorToLog(w, "conv1_weight.log")
|
||||
|
||||
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]), dir + "/conv1_output.png", Contrast=[-1.0, 1.0])
|
||||
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]), dir + "/conv1_output.png")
|
||||
# show.DumpTensorToLog(x, "conv1_output.png")
|
||||
|
||||
x = self.pool(x)
|
||||
x = self.conv2(x)
|
||||
w = self.conv2.weight
|
||||
show.DumpTensorToImage(
|
||||
w.view(-1, w.shape[2], w.shape[3]).cpu(), dir + "/conv2_weight.png", Contrast=[-1.0, 1.0]
|
||||
)
|
||||
show.DumpTensorToImage(
|
||||
x.view(-1, x.shape[2], x.shape[3]).cpu(), dir + "/conv2_output.png", Contrast=[-1.0, 1.0]
|
||||
)
|
||||
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]).cpu(), dir + "/conv2_weight.png")
|
||||
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]).cpu(), dir + "/conv2_output.png")
|
||||
x = self.pool(x)
|
||||
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]).cpu(), dir + "/pool_output.png", Contrast=[-1.0, 1.0])
|
||||
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]).cpu(), dir + "/pool_output.png")
|
||||
pool_shape = x.shape
|
||||
x = x.view(x.shape[0], -1)
|
||||
x = self.fc1(x)
|
||||
|
|
@ -105,14 +105,27 @@ model = ConvNet().to(device)
|
|||
model.train()
|
||||
|
||||
# Train the model unsuper
|
||||
epochs = 20
|
||||
model.conv1.weight.requires_grad = True
|
||||
model.conv2.weight.requires_grad = False
|
||||
model.fc1.weight.requires_grad = False
|
||||
epochs = 1
|
||||
n_total_steps = len(train_loader)
|
||||
for epoch in range(epochs):
|
||||
for i, (images, labels) in enumerate(train_loader):
|
||||
images = images.to(device)
|
||||
|
||||
# # images = images[:,:,12:15,12:15]
|
||||
# kernel_size = 3
|
||||
# mean_filter = torch.ones((1, 1, kernel_size, kernel_size), device=device) / (kernel_size * kernel_size)
|
||||
# images = F.conv2d(images, mean_filter, padding=1)
|
||||
# images = F.conv2d(images, mean_filter, padding=1)
|
||||
# images = F.conv2d(images, mean_filter, padding=1)
|
||||
# # images = F.conv2d(images, mean_filter, padding=1)
|
||||
# # images = F.conv2d(images, mean_filter, padding=1)
|
||||
|
||||
# images = torch.rand(3, 3).to(device=device)
|
||||
# # images[1, 1] = images[1, 1] * 2
|
||||
# # images[0, 0] = images[1, 1] * 2
|
||||
# # images[2, 2] = images[1, 1] * 2
|
||||
# images = images.view(1, 1, 3, 3)
|
||||
|
||||
outputs = model.forward_unsuper(images)
|
||||
|
||||
outputs = outputs.permute(0, 2, 3, 1) # 64 8 24 24 -> 64 24 24 8
|
||||
|
|
@ -134,15 +147,16 @@ for epoch in range(epochs):
|
|||
model.conv1.weight.grad = None
|
||||
loss.backward()
|
||||
|
||||
model.conv1.weight.data = model.conv1.weight.data - model.conv1.weight.grad * 10
|
||||
model.conv1.weight.data = model.conv1.weight.data - model.conv1.weight.grad * 100
|
||||
|
||||
if (i + 1) % 100 == 0:
|
||||
print(f"Epoch [{epoch+1}/{epochs}], Step [{i+1}/{n_total_steps}], Loss: {loss.item():.8f}")
|
||||
|
||||
w = model.conv1.weight.grad
|
||||
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]).cpu(), "conv1_weight_grad.png")
|
||||
show.DumpTensorToImage(images.view(-1, images.shape[2], images.shape[3]), "input_image.png", Contrast=[0, 1.0])
|
||||
g = model.conv1.weight.grad
|
||||
show.DumpTensorToImage(g.view(-1, g.shape[2], g.shape[3]).cpu(), "conv1_weight_grad.png")
|
||||
w = model.conv1.weight.data
|
||||
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]), "conv1_weight_update.png", Contrast=[-1.0, 1.0])
|
||||
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]), "conv1_weight_update.png")
|
||||
|
||||
# loader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False)
|
||||
# images, labels = next(iter(loader))
|
||||
|
|
|
|||
Loading…
Reference in New Issue