Advertisement
Guest User

Untitled

a guest
Mar 30th, 2022
170
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 3.72 KB | None | 0 0
  1. WARNING:tensorflow:Functional model inputs must come from `tf.keras.Input` (thus holding past layer metadata). They cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "model_9" was not an Input tensor, it was generated by layer "conv2d_0_input".
  2. Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
  3. The tensor that caused the issue was: KerasTensor(type_spec=TensorSpec(shape=(None, 28, 28, 1), dtype=tf.float32, name='conv2d_0_input'), name='conv2d_0_input', description="created by layer 'conv2d_0_input'")
  4. 2022-03-31 02:34:38,296 -WARNING - _validate_graph_inputs_and_outputs - Functional model inputs must come from `tf.keras.Input` (thus holding past layer metadata). They cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "model_9" was not an Input tensor, it was generated by layer "conv2d_0_input".
  5. Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
  6. The tensor that caused the issue was: KerasTensor(type_spec=TensorSpec(shape=(None, 28, 28, 1), dtype=tf.float32, name='conv2d_0_input'), name='conv2d_0_input', description="created by layer 'conv2d_0_input'")
  7. Iteration: 0 of 32 (12000, 128) 2 1.0079994180253746 (12000, 128) True {'acc_before': 0.987333357334137, 'acc_after': 0.987500011920929, 'weights_before': 599432, 'weights_after': 587144, 'was_conv': False}
  8. Model: "model_8"
  9. __________________________________________________________________________________________________
  10. Layer (type) Output Shape Param # Connected to
  11. ==================================================================================================
  12. conv2d_0_input (InputLayer) multiple 0 ['conv2d_0_input[0][0]']
  13.  
  14. conv2d_0 (Conv2D) (None, 26, 26, 32) 320 ['conv2d_0_input[1][0]']
  15.  
  16. conv2d_1/DepthwiseSeparableLay (None, 24, 24, 32) 1344 ['conv2d_0[2][0]']
  17. er (SeparableConv2D)
  18.  
  19. max_pooling2d (MaxPooling2D) (None, 12, 12, 32) 0 ['conv2d_1/DepthwiseSeparableLaye
  20. r[1][0]']
  21.  
  22. flatten (Flatten) (None, 4608) 0 ['max_pooling2d[2][0]']
  23.  
  24. dense_0/DeepCompression (Dense (None, 128) 589952 ['flatten[2][0]']
  25. )
  26.  
  27. dense_1/DenseSVDC (DenseSVD) (None, 128) 4224 ['dense_0/DeepCompression[2][0]']
  28.  
  29. dense_softmax (Dense) (None, 10) 1290 ['dense_1/DenseSVDC[0][0]']
  30.  
  31. ==================================================================================================
  32. Total params: 597,130
  33. Trainable params: 597,130
  34. Non-trainable params: 0
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement