nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_tensor.unsqueeze_(dim=2) # B*C*H*W to B*C*D*H*W 一般三维卷积对5维张量（多了时间维度）计算
img_conv = conv_layer(img_tensor)
# ================ transposed
if flag == 't':
conv_layer = nn.ConvTranspose2d(3, 1, 3, stride=2) # input:(i, o, size)
nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_conv = conv_layer(img_tensor)
# ================================= visualization ==================================
print("卷积前尺寸:{}\n卷积后尺寸:{}".format(img_tensor.shape, img_conv.shape))
if flag == '3d':
img_raw = transform_invert(img_tensor.squeeze(), img_transform)
img_conv = transform_invert(img_conv.squeeze(), img_transform)
else:
img_raw = transform_invert(img_tensor.squeeze(), img_transform)
img_conv = transform_invert(img_conv[0, 0:1, ...],
img_transform) # 0:1可以保留这个维度
plt.figure(figsize=(16, 16))
plt.subplot(121).imshow(img_raw)
plt.subplot(122).imshow(img_conv, cmap='gray')
plt.show()
# ============================ inference ============================
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
test_dir = os.path.join(BASE_DIR, "test_data")
test_data = RMBDataset(data_dir=test_dir, transform=valid_transform)
valid_loader = DataLoader(dataset=test_data, batch_size=1)
for i, data in enumerate(valid_loader):
# forward
inputs, labels = data
outputs = net(inputs)
_, predicted = torch.max(outputs.data, 1)
rmb = 1 if predicted.numpy()[0] == 0 else 100
img_tensor = inputs[0, ...] # C H W
img = transform_invert(img_tensor, train_transform)
plt.imshow(img)
plt.title("LeNet got {} Yuan".format(rmb))
plt.show()
plt.pause(0.5)
plt.close()
plt.plot(valid_x, valid_y, label='Valid')
plt.legend(loc='upper right')
plt.ylabel('loss value')
plt.xlabel('Iteration')
plt.show()
# ============================ inference ============================
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
test_dir = os.path.join(BASE_DIR, "test_data")
test_data = RMBDataset(data_dir=test_dir, transform=valid_transform)
valid_loader = DataLoader(dataset=test_data, batch_size=1)
for i, data in enumerate(valid_loader):
# forward
inputs, labels = data
outputs = net(inputs)
_, predicted = torch.max(outputs.data, 1)
rmb = 1 if predicted.numpy()[0] == 0 else 100
img_tensor = inputs[0, ...] # C H W
img = transform_invert(img_tensor, valid_transform)
plt.imshow(img)
plt.title("LeNet got {} Yuan".format(rmb))
plt.show()
plt.pause(0.5)
plt.close()
img_tensor.unsqueeze_(dim=0) # C*H*W to B*C*H*W
# ================ 3d kernel (1, 3, 3)
# flag = 1
flag = 0
if flag:
conv_layer = nn.Conv3d(3, 1, (1, 3, 3), padding=(1, 0, 0), bias=False)
nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_tensor.unsqueeze_(dim=2) # B*C*H*W to B*C*D*H*W
img_conv = conv_layer(img_tensor)
# ================================= visualization ==================================
print("卷积前尺寸:{}\n卷积后尺寸:{}".format(img_tensor.shape, img_conv.shape))
img_conv = transform_invert(img_conv.squeeze(), img_transform)
img_raw = transform_invert(img_tensor.squeeze(), img_transform)
plt.subplot(122).imshow(img_conv, cmap='gray')
plt.subplot(121).imshow(img_raw)
plt.show()
# ================ 3d kernel (3, 3, 3)
flag = 1
# flag = 0
if flag:
conv_layer = nn.Conv3d(3, 1, (3, 3, 3), padding=(1, 0, 0), bias=False)
nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_tensor.unsqueeze_(dim=2) # B*C*H*W to B*C*D*H*W
img_conv = conv_layer(img_tensor)
img_reconstruct = torch.randn_like(img_pool, dtype=torch.float)
maxunpool_layer = nn.MaxUnpool2d((2, 2), stride=(2, 2))
img_unpool = maxunpool_layer(img_reconstruct, indices)
print("raw_img:\n{}\nimg_pool:\n{}".format(img_tensor, img_pool))
print("img_reconstruct:\n{}\nimg_unpool:\n{}".format(
img_reconstruct, img_unpool))
# ================ linear
# flag = 1
flag = 0
if flag:
inputs = torch.tensor([[1., 2, 3]])
linear_layer = nn.Linear(3, 4)
linear_layer.weight.data = torch.tensor([[1., 1., 1.], [2., 2., 2.],
[3., 3., 3.], [4., 4., 4.]])
linear_layer.bias.data.fill_(0.5)
output = linear_layer(inputs)
print(inputs, inputs.shape)
print(linear_layer.weight.data, linear_layer.weight.data.shape)
print(output, output.shape)
# ================================= visualization ==================================
print("池化前尺寸:{}\n池化后尺寸:{}".format(img_tensor.shape, img_pool.shape))
img_pool = transform_invert(img_pool[0, 0:3, ...], img_transform)
img_raw = transform_invert(img_tensor.squeeze(), img_transform)
plt.subplot(122).imshow(img_pool)
plt.subplot(121).imshow(img_raw)
plt.show()
# flag = 1
flag = 0
if flag:
conv_layer = nn.Conv2d(
3, 1,
3) # input:(i, o, size) weights:(o, i , h, w) 输入通道3，输出通道1，卷积核为3*3
nn.init.xavier_normal_(
conv_layer.weight.data) # 采用xavier的方法对上一行创建的卷积层进行初始化
# calculation 输入图片张量进入卷积层
img_conv = conv_layer(img_tensor)
# ================ transposed 创建2维正常卷积=================================================
flag = 1
# flag = 0
if flag:
conv_layer = nn.ConvTranspose2d(3, 1, 3, stride=2) # input:(i, o, size)
nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_conv = conv_layer(img_tensor)
# ================================= visualization ==================================
print("卷积前尺寸:{}\n卷积后尺寸:{}".format(img_tensor.shape, img_conv.shape))
img_conv = transform_invert(img_conv[0, 0:1, ...],
img_transform) # 对卷积后的张量进行逆操作以显示卷积后的图像
img_raw = transform_invert(img_tensor.squeeze(), img_transform)
plt.subplot(122).imshow(img_conv, cmap='gray')
plt.subplot(121).imshow(img_raw)
plt.show()
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std),
])
net = torch.load("./1.pth")
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
test_dir = os.path.join(BASE_DIR, "test_data")
test_data = DogCatDataset(data_dir=test_dir, transform=valid_transform)
valid_loader = DataLoader(dataset=test_data, batch_size=1)
# net = MyNet(classes=2)
for i, data in enumerate(valid_loader):
# forward
inputs, labels = data
inputs = inputs.to("cuda")
labels = labels.to("cuda")
outputs = net(inputs)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net = net.to(device)
_, predicted = torch.max(outputs.data.cpu(), 1)
rmb = 'dog' if predicted.numpy()[0] == 0 else 'cat'
print("模型获得动物是{}".format(rmb))
img_tensor = inputs[0, ...] # c H W
img = transform_invert(img_tensor.cpu(), train_transform)
plt.imshow(img)
plt.title("LeNet got {} Yuan".format(rmb))
plt.show()
plt.pause(0.5)
plt.close()
