ValueError: Error when checking input: expected lstm_1_input to have shape (None, 296, 2048) but got array with shape (296, 2048, 1)

Question

I am facing the error in the title. I have thousands of videos and each video have 37 frames. I have extracted features for each frame with a CNN model and saved them. I have a stacked LSTM model :

batch_size = 8
features_length = 2048
seq_length = 37*batch_size
in_shape = (seq_length, features_length)
lstm_model = Sequential()
lstm_model.add(LSTM(2048, return_sequences=True, input_shape = in_shape, dropout=0.5))
lstm_model.add(Flatten())
lstm_model.add(Dense(512, activation='relu'))
lstm_model.add(Dropout(0.5))
lstm_model.add(Dense(number_of_classes, activation='softmax'))
optimizer = Adam(lr=1e-6)
lstm_model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics = metrics)
lstm_model.fit_generator(generator = generator, steps_per_epoch = train_steps_per_epoch, epochs = nb_epoch, verbose = 1, callbacks=[checkpointer, tb, early_stopper, csv_logger], validation_data=val_generator, validation_steps = val_steps_per_epoch)

I have a generator; data includes all training videos.

def generator(data):

    while 1:
        X, y = [], []
        for _ in range(batch_size):
            sequence = None
            sample = random.choice(data)
            folder_content, folder_name, class_name, video_features_loc = get_video_features(sample)
            for f in folder_content:
                image_feature_location = video_features_loc + f
                feat = get_extracted_feature(image_feature_location)

                X.append(feat)
                y.append(get_one_class_rep(class_name))         
        yield np.array(X), np.array(y)

The shape of X in generator data is = (296, 2048, 1)

The shape of y in generator data is = (296, 27)

This code throws the error. I know there are couple of similar questions. I tried the suggestions there but no luck. For instance one the suggestions was reshaping the array;

X = np.reshape(X, (X.shape[2], X.shape[0], X.shape[1]))

How could I feed my input to the LSTM?

Thanks in advance

X = np.reshape(X, (X.shape[2], X.shape[0], X.shape[1]))

Daniel Möller
– Daniel Möller

2017-09-08 14:36:19 +00:00
Commented Sep 8, 2017 at 14:36 — Daniel Möller
– Daniel Möller, Commented Sep 8, 2017 at 14:36

Daniel Möller · Accepted Answer · 2017-09-09 19:37:11Z

2

The error message tells you everything you need.

X should be shaped as (number of samples, 296, 2048) - It seems you have one sample only, by the shape of X.

But if you have 37 frames, you should definitely change your model for something accepting: (Batch size, 37, 2048) - Here, batch size seems to be 8.

seq_length=37

edited Sep 9, 2017 at 19:37

answered Sep 8, 2017 at 14:09

Daniel Möller

86.8k24 gold badges202 silver badges222 bronze badges

Sign up to request clarification or add additional context in comments.

3 Comments

yns Over a year ago

Thanks very much for your answer @Daniel. I changed X shape as you said; (1, 296, 2048) 1 is the number of sample. However this time I got the error; "ValueError: Input arrays should have the same number of samples as target arrays. Found 1 input samples and 296 target samples."

yns Over a year ago

I kind of know that this error is about having different size of X and y values. I have been dealing with LSTMs for a month now in Keras. I got stuck with these input shapes every time I try to use LSTMs in Keras...

Daniel Möller Over a year ago

Just shape X according to what you actually have: (NumberOfExamples = numberOfVideos, TimeSteps = framesInAVideo, featuresInAFrame or pixelsInAFrame) -- Once you understand your data and shape it correctly, then you make input_shape=(TimeSteps,features).

Collectives™ on Stack Overflow

ValueError: Error when checking input: expected lstm_1_input to have shape (None, 296, 2048) but got array with shape (296, 2048, 1)

1 Answer 1

3 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

3 Comments

Your Answer

Sign up or log in

Post as a guest

Related