2

A few things come to mind here: If you are using a pre-trained MobileNetV2 on a task which is similar to the pre-training, then you may not need much fine-tuning to get good results. This may explain why you are seeing good training results. For the poor testing results, are you transforming your frames in the same way you did for training? Any differences ...


1

You will judge the performance of the trained model based on certain performance metrics. If you keep updating your test set, then you will not know whether one run is better than the other. For e.g. you are trying to predict the value of house. And you have only one data point in your test set and you are using mean absolute error (MAE) as your performance ...


1

So the question asks why you are seeing a decrease in the loss function (for both training and validation?), but you are also observing decreasing generalisation performance over iterations. One first thought could be due to the loss function that you have chosen might not be appropriate for your task.


1

Like you correctly pointed out, your data is actually sequential. Simply randomly splitting your data for training and testing won't do here. If you do it like that it is very likely that every test frame is only 5 frames away from a training frame making it look very similar. Your network has practically seen your testing data in training already. You will ...


1

There can be a few reasons for this behavior as already pointed out in "Why is the validation accuracy fluctuating?": Size of train / validation stes: Fluctuations may become stronger the smaller your validation set is, especially during the early stage of training where predictions are closer to random predictions. Overfitting: Train loss seems ...


1

You should set the input_shape parameter in the first dense layer. Like this: model = Sequential() model.add(Dense(12, activation='linear', input_shape=(33222,))) model.add(Dense(1, activation='linear'))


1

I also have been looking for answers regarding this before, and after several days of trying with my friend, we manage to do it. I attach some code snippet that we use, you may modify it according to your use case image = '763104351884.dkr.ecr.us-east-1.amazonaws.com/tensorflow-inference:2.2.0-cpu' container = { 'Image': image, 'ModelDataUrl': ...


1

Since you are only using one class for training, you can't expect the network to understand what the object is not. For example, if you want to classify cats you have to pass to the network images that are not in your main class [dogs, cars, boats, random_noise, penguins]. If you try to pass any other image to your current model it will answer with great ...


1

You can see the metrics value for each threshold along the fitting process if you explicitely instantiate the corresponding metric class for each threshold, as follows: model.compile( optimizer=keras.optimizers.Adam(learning_rate=1e-2), loss='categorical_crossentropy', metrics=[metrics.Recall(thresholds=0.6), metrics.Recall(thresholds=0.9)]) model....


1

I solved the problem using subclassing in keras. The code is shown below: class Wt_Add(keras.layers.Layer): def __init__(self, units=1, input_dim=1): super(Wt_Add, self).__init__() w_init = tf.random_normal_initializer() self.w1 = tf.Variable( initial_value=w_init(shape=(input_dim, units), dtype="float32"), trainable=...


1

To summarize, the notebook describes three key components: The state, which completely describes the system at any given time. A SEIR model by definition has four variables in the state: susceptible, exposed, infected, and reported. The dynamics, which describe how the states evolve over time. The measured parameters for the dynamic equations: $\beta$, $\mu$...


Only top voted, non community-wiki answers of a minimum length are eligible