Input 0 of layer "dense_2" is incompatible with the layer: expected axis -1 of input shape to have value 16384, but received input with shape (None, 65536)

[coder-monishr]

Hey there!! This is the issue I get

ValueError: Exception encountered when calling Sequential.call().

Input 0 of layer "dense_2" is incompatible with the layer: expected axis -1 of input shape to have value 16384, but received input with shape (None, 65536)

Arguments received by Sequential.call():
• inputs=tf.Tensor(shape=(None, 256, 256, 3), dtype=float32)
• training=True
• mask=None

code is here!
history = model.fit(x=training_set,validation_data=validation_set, epochs=10)

[coder-monishr]

@sachinprasadhs help me out

[sachinprasadhs]

Could you please provide reproducible code in a colab Gist to understand more on the issue. Thanks!

[coder-monishr]

@sachinprasadhs yeaa

https://colab.research.google.com/drive/1QyLNRMwOhuMpZ_4_eJ5m3pKh2Np_wG7g?usp=sharing

[sachinprasadhs]

You are restricting the input_shape for each convolution operation to be 128,128,3, which does not fit to the actual data size which you are passing which is 256,256,3, replacing your code with below code should work.

from keras.layers import Dense, Conv2D, MaxPool2D, Flatten
from keras.models import Sequential

model = Sequential()

model.add(Conv2D(filters=32, kernel_size=3, padding="same", activation="relu",input_shape=[256,256,3]))
model.add(Conv2D(filters=32, kernel_size=3, padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=2,strides=2))

model.add(Conv2D(filters=64, kernel_size=3, padding="same", activation="relu"))
model.add(Conv2D(filters=64, kernel_size=3, padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=2,strides=2))


model.add(Conv2D(filters=128, kernel_size=3, padding="same", activation="relu"))
model.add(Conv2D(filters=128, kernel_size=3, padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=2,strides=2))

model.add(Conv2D(filters=256, kernel_size=3, padding="same", activation="relu"))
model.add(Conv2D(filters=256, kernel_size=3, padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=2,strides=2))

model.add(Flatten())

model.add(Dense(units = 1024, activation="relu"))

model.add(Dense(units = 1024, activation="relu"))

model.add(Dense(units = 38, activation="softmax"))

model.compile(optimizer = "adam", loss ='categorical_crossentropy', metrics=['accuracy'])

[coder-monishr]

history = model.fit(x=training_set, validation_data=validation_set, epochs=10)

ValueError Traceback (most recent call last)
Cell In[12], line 1
----> 1 history = model.fit(x=training_set, validation_data=validation_set, epochs=10)

File /Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/keras/src/utils/traceback_utils.py:123, in filter_traceback..error_handler(*args, **kwargs)
120 filtered_tb = _process_traceback_frames(e.traceback)
121 # To get the full stack trace, call:
122 # keras.config.disable_traceback_filtering()
--> 123 raise e.with_traceback(filtered_tb) from None
124 finally:
125 del filtered_tb

File /Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/keras/src/backend/tensorflow/nn.py:546, in categorical_crossentropy(target, output, from_logits, axis)
540 raise ValueError(
541 "Arguments target and output must be at least rank 1. "
542 "Received: "
543 f"target.shape={target.shape}, output.shape={output.shape}"
544 )
545 if len(target.shape) != len(output.shape):
--> 546 raise ValueError(
547 "Arguments target and output must have the same rank "
548 "(ndim). Received: "
549 f"target.shape={target.shape}, output.shape={output.shape}"
550 )
551 for e1, e2 in zip(target.shape, output.shape):
552 if e1 is not None and e2 is not None and e1 != e2:

ValueError: Arguments target and output must have the same rank (ndim). Received: target.shape=(None,), output.shape=(None, 38)

still i get the error dude! :(

[sachinprasadhs]

It is basically the number of classes you are using, if the data is a binary classification then you need to change the output layer to something like model.add(Dense(units = 1, activation="sigmoid"))

[coder-monishr]

Thank you so much bro solved

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No