scenarios in TensorFlow model fitting: Input shapes mismatch during training
Quick question that's been bugging me - I'm relatively new to this, so bear with me... I tried several approaches but none seem to work. I'm currently working on a regression model using TensorFlow 2.6 and I've run into an scenario where my input shapes seem to be mismatched during the model fitting process. I'm using a dataset with 1000 samples and 10 features, but when I try to fit the model, I get the following behavior: ``` ValueError: Shapes (None, 1) and (None, 10) are incompatible ``` Here's a snippet of the code I'm using to define my model: ```python import tensorflow as tf from tensorflow.keras import layers, models # Load data import numpy as np X = np.random.rand(1000, 10) y = np.random.rand(1000, 1) # Define the model model = models.Sequential() model.add(layers.Dense(64, activation='relu', input_shape=(10,))) model.add(layers.Dense(1)) model.compile(optimizer='adam', loss='mean_squared_error') # Attempt to fit the model model.fit(X, y, epochs=10, batch_size=32) ``` I have verified that `X` has the shape `(1000, 10)` and `y` has the shape `(1000, 1)`, so I don't understand why I'm getting this behavior. I've also tried reshaping `y` using `y.reshape(-1, 1)` but that hasn't resolved the scenario. I suspect it might be related to how I'm defining the loss function or compiling the model, but I'm not sure. Can anyone provide some insight into what might be going wrong here and how to fix it? Has anyone else encountered this? For context: I'm using Python on Windows. Thanks in advance! My development environment is Linux. Any ideas what could be causing this?