# Tag Info

0

I was able to get over this error by changing the target size from target_size=(224, 224) to target_size=(1,224, 224) I hope this may help another one.

0

First of all, are you sure you are using a MSE loss? If so, the loss should go hand in hand with your metric (MSE), especially since I see no Masking layer in your network. Plus, the MSE loss is not below zero, that would be impossible anyway. Additionally, the graph you provided does not match the numbers shown above. Does it come from different runs? ...

0

To answer your questions first This paper assume $f_i$ is sigmoid function $f_i(x) = \sigma(x) = \frac{1}{1 + e^{-x}}$. Note that $$\frac{\partial \sigma(x)}{\partial x} = \sigma(x) (1 - \sigma(x))$$ Since  \begin{align*} & f'_{l_m}\big(\text{net}_{l_m}(t - m)\big) w_{l_m l_{m - 1}} \\ & = \sigma\big(\text{net}_{l_m}(t - m)\big) \cdot \Big(1 - \...

1

It seems a couple of things can be done differently. Firstly, it seems you are passing train and label data incorrectly when fitting the model. It should be more like: model.compile(loss='mean_squared_error', optimizer='adam') model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2) For trainY being your labels, as opposed to passing trainX twice as ...

1

Generally, you can indeed consider adding more layers and batchnorm/dropout to a neural network a means for controlling bias and variance of your model, respectively. However, increasing variance by stacking more layers doesn't always at all mean that you overfit your model. To diagnose that you are actually overfitting you should see that your training loss ...

0

If you haven't stratified the splot of train/val/test sets, I would suggest checking class ratio in train set class ration in val set class ration in test set

Top 50 recent answers are included