Running on local URL:  http://localhost:7860/

To create a public link, set `share=True` in `launch()`.
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)Running on local URL:  http://localhost:7860/

To create a public link, set `share=True` in `launch()`.
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)Running on local URL:  http://localhost:7860/

To create a public link, set `share=True` in `launch()`.
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(270, 480, 3)
(2160, 3840, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(255, 255, 3)
(255, 255, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(600, 270, 3)
(2400, 1080, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(480, 216, 3)
(1920, 864, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(480, 216, 3)
(1920, 864, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(270, 585, 3)
(1080, 2340, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(480, 216, 3)
(1920, 864, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
Illumination_Alone(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv5): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
  (leaky_relu_1): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_2): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_3): LeakyReLU(negative_slope=0.2, inplace=True)
  (leaky_relu_4): LeakyReLU(negative_slope=0.2, inplace=True)
  (relu): ReLU()
)
Adjust_naive(
  (conv1): Conv2d(2, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv3): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv4): Conv2d(32, 1, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (leaky_relu): LeakyReLU(negative_slope=0.2)
  (relu): ReLU()
)
(342, 456, 3)
(2736, 3648, 3)
img_path ./demo/input/3.png
output ./demo/output
ratio 5
Decom_model_low_path ./ckpt/init_low.pth
unfolding_model_path ./ckpt/unfolding.pth
adjust_model_path ./ckpt/L_adjust.pth
gpu_id 0
 ===========>  loading pretrained Illumination Adjustment Model from: ./ckpt/L_adjust.pth 
Decom(
  (decom): Sequential(
    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): LeakyReLU(negative_slope=0.2, inplace=True)
    (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): LeakyReLU(negative_slope=0.2, inplace=True)
    (4): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): LeakyReLU(negative_slope=0.2, inplace=True)
    (6): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
  )
)
HalfDnCNNSE(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU(inplace=True)
  (conv2): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu2): ReLU(inplace=True)
  (se_layer): SELayer(
    (avg_pool): AdaptiveAvgPool2d(output_size=1)
    (fc): Sequential(
      (0): Linear(in_features=64, out_features=4, bias=False)
      (1): ReLU(inplace=True)
      (2): Linear(in_features=4, out_features=64, bias=False)
      (3): Sigmoid()
    )
  )
  (conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu3): ReLU(inplace=True)
  (conv4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu4): ReLU(inplace=True)
  (conv5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu5): ReLU(inplace=True)
  (conv6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu6): ReLU(inplace=True)
  (conv7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu7): ReLU(inplace=True)
  (conv8): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.
WARNING:  Invalid HTTP request received.