After the first training I get a strange error
Posted: Thu Jun 22, 2023 6:06 pm
Hi,i just want to ask this error
Everything was fine the first time I finished training, but when I did my second training it just popped up with this message
Code: Select all
Model: "encoder"
____________________________________________________________________________________________________
Layer (type) Output Shape Param #
====================================================================================================
input_1 (InputLayer) [(None, 64, 64, 3)] 0
conv_128_0_conv2d (Conv2D) (None, 32, 32, 128) 9728
conv_128_0_leakyrelu (LeakyReLU) (None, 32, 32, 128) 0
conv_256_0_conv2d (Conv2D) (None, 16, 16, 256) 819456
conv_256_0_leakyrelu (LeakyReLU) (None, 16, 16, 256) 0
conv_512_0_conv2d (Conv2D) (None, 8, 8, 512) 3277312
conv_512_0_leakyrelu (LeakyReLU) (None, 8, 8, 512) 0
conv_1024_0_conv2d (Conv2D) (None, 4, 4, 1024) 13108224
conv_1024_0_leakyrelu (LeakyReLU) (None, 4, 4, 1024) 0
flatten (Flatten) (None, 16384) 0
dense (Dense) (None, 1024) 16778240
dense_1 (Dense) (None, 16384) 16793600
reshape (Reshape) (None, 4, 4, 1024) 0
upscale_512_0_conv2d_conv2d (Conv2D) (None, 4, 4, 2048) 18876416
upscale_512_0_conv2d_leakyrelu (LeakyReLU) (None, 4, 4, 2048) 0
upscale_512_0_pixelshuffler (PixelShuffler) (None, 8, 8, 512) 0
====================================================================================================
Total params: 69,662,976
Trainable params: 69,662,976
Non-trainable params: 0
____________________________________________________________________________________________________
Model: "decoder_a"
____________________________________________________________________________________________________
Layer (type) Output Shape Param #
====================================================================================================
input_2 (InputLayer) [(None, 8, 8, 512)] 0
upscale_256_0_conv2d_conv2d (Conv2D) (None, 8, 8, 1024) 4719616
upscale_256_0_conv2d_leakyrelu (LeakyReLU) (None, 8, 8, 1024) 0
upscale_256_0_pixelshuffler (PixelShuffler) (None, 16, 16, 256) 0
upscale_128_0_conv2d_conv2d (Conv2D) (None, 16, 16, 512) 1180160
upscale_128_0_conv2d_leakyrelu (LeakyReLU) (None, 16, 16, 512) 0
upscale_128_0_pixelshuffler (PixelShuffler) (None, 32, 32, 128) 0
upscale_64_0_conv2d_conv2d (Conv2D) (None, 32, 32, 256) 295168
upscale_64_0_conv2d_leakyrelu (LeakyReLU) (None, 32, 32, 256) 0
upscale_64_0_pixelshuffler (PixelShuffler) (None, 64, 64, 64) 0
face_out_a_conv2d (Conv2D) (None, 64, 64, 3) 4803
face_out_a (Activation) (None, 64, 64, 3) 0
====================================================================================================
Total params: 6,199,747
Trainable params: 6,199,747
Non-trainable params: 0
____________________________________________________________________________________________________
Model: "decoder_b"
____________________________________________________________________________________________________
Layer (type) Output Shape Param #
====================================================================================================
input_3 (InputLayer) [(None, 8, 8, 512)] 0
upscale_256_1_conv2d_conv2d (Conv2D) (None, 8, 8, 1024) 4719616
upscale_256_1_conv2d_leakyrelu (LeakyReLU) (None, 8, 8, 1024) 0
upscale_256_1_pixelshuffler (PixelShuffler) (None, 16, 16, 256) 0
upscale_128_1_conv2d_conv2d (Conv2D) (None, 16, 16, 512) 1180160
upscale_128_1_conv2d_leakyrelu (LeakyReLU) (None, 16, 16, 512) 0
upscale_128_1_pixelshuffler (PixelShuffler) (None, 32, 32, 128) 0
upscale_64_1_conv2d_conv2d (Conv2D) (None, 32, 32, 256) 295168
upscale_64_1_conv2d_leakyrelu (LeakyReLU) (None, 32, 32, 256) 0
upscale_64_1_pixelshuffler (PixelShuffler) (None, 64, 64, 64) 0
face_out_b_conv2d (Conv2D) (None, 64, 64, 3) 4803
face_out_b (Activation) (None, 64, 64, 3) 0
====================================================================================================
Total params: 6,199,747
Trainable params: 6,199,747
Non-trainable params: 0
____________________________________________________________________________________________________
Model: "original"
____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
face_in_a (InputLayer) [(None, 64, 64, 3)] 0 []
face_in_b (InputLayer) [(None, 64, 64, 3)] 0 []
encoder (Functional) (None, 8, 8, 512) 69662976 ['face_in_a[0][0]',
'face_in_b[0][0]']
decoder_a (Functional) (None, 64, 64, 3) 6199747 ['encoder[0][0]']
decoder_b (Functional) (None, 64, 64, 3) 6199747 ['encoder[1][0]']
====================================================================================================
Total params: 82,062,470
Trainable params: 82,062,470
Non-trainable params: 0
____________________________________________________________________________________________________
Process exited.