Number of channels in convLSTM for classifying videos

user_13647248 0
Viewed 182

I created a convLSTM for classifying videos in grayscale, that means they have a single channel. Even if i defined 1 as the number of channels i get the error:

ValueError: Error when checking input: expected conv_lst_m2d_1_input to have 5 dimensions, but got array with shape (128, 176, 256, 256)

128 is the size of the training dataset, 176*256 is the resolution of every frame and 256 is the number of frame in each video.

X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.20, shuffle=True, random_state=0)
 
model = Sequential()
model.add(ConvLSTM2D(filters = 64, kernel_size = (3, 3), return_sequences = False, data_format = "channels_last", input_shape = (seq_len, img_height, img_width, 1)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(256, activation="relu"))
model.add(Dropout(0.3))
model.add(Dense(6, activation = "softmax"))
 
model.summary()
 
opt = keras.optimizers.SGD(lr=0.001)
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=["accuracy"])
 
earlystop = EarlyStopping(patience=7)
callbacks = [earlystop]

history = model.fit(x = X_train, y = y_train, epochs=40, batch_size = 8 , shuffle=True, validation_split=0.2, callbacks=callbacks)
keras tensorflow machine-learning neural-network python
1 Answers

you simply need to expand the last dimension of your data

batch_dim, seq_len, img_height, img_width = 3, 17, 25, 25
X = np.random.uniform(0,1, (batch_dim, seq_len, img_height, img_width))
y = np.random.randint(0,6, batch_dim)
print(X.shape)

# expand input dimension
X = X[...,np.newaxis]
print(X.shape)

model = Sequential()
model.add(ConvLSTM2D(filters = 64, kernel_size = (3, 3), return_sequences = False, 
                     data_format = "channels_last", 
                     input_shape = (seq_len, img_height, img_width, 1)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(256, activation="relu"))
model.add(Dropout(0.3))
model.add(Dense(6, activation = "softmax"))
model.summary()

model.predict(X).shape
user_103750490
Related