We Keep Coding

Cannot resolve error in keras sequential model

I am working on a gesture recognition problem. For that I have a train set. Train set consists of multiple folders and each folder consists of a series of 30 images. From those images the model is trained. Also I have a csv file that contains the class label of each folder. The class labels are : "Left Swipe", "Right Swipe", "Stop", "Thumbs Down" and "Thumbs Up". Those labels are present in one np.array variable train_class. Now, I have created a CNN model then feeding that in a Sequential model.
The code is available in below GIT location
https://github.com/subhrajyoti-ghosh/ML-and-Deep-Learning/blob/main/Gesture_Recognition.ipynb
But when I am trying to fit the model, I am receiving error. Can you please help me understanding the error and how to solve that?

You are trying to use a TimeDistributed layer on a 2D input (batch_size, 256), which will not work, because the layer needs at least a 3D tensor. You should try using tf.keras.layers.RepeatVector:
import tensorflow as tf
resnet = tf.keras.applications.ResNet50(include_top=False,weights='imagenet',input_shape=(224,224,3))
cnn = tf.keras.Sequential([resnet])
cnn.add(tf.keras.layers.Conv2D(64,(2,2),strides=(1,1)))
cnn.add(tf.keras.layers.Conv2D(16,(3,3),strides=(1,1)))
cnn.add(tf.keras.layers.Flatten())
inputs = tf.keras.layers.Input(shape=(224,224,3))
x = cnn(inputs)
x = tf.keras.layers.RepeatVector(n=30)(x)
x = tf.keras.layers.GRU(16,return_sequences=True)(x)
x = tf.keras.layers.GRU(8)(x)
outputs = tf.keras.layers.Dense(5,activation='softmax')(x)
model = tf.keras.Model(inputs, outputs)
dummy_x = tf.random.normal((1, 224,224,3))
print(model.summary())
print(model(dummy_x))
Model: "model_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_14 (InputLayer) [(None, 224, 224, 3)] 0
sequential_6 (Sequential) (None, 256) 24121296
repeat_vector_2 (RepeatVect (None, 30, 256) 0
or)
gru_5 (GRU) (None, 30, 16) 13152
gru_6 (GRU) (None, 8) 624
dense_7 (Dense) (None, 5) 45
=================================================================
Total params: 24,135,117
Trainable params: 24,081,997
Non-trainable params: 53,120
_________________________________________________________________
None

Keras, simple model, shapes incompatible, but why?

I'm working on a first model in Keras, just to get started. I downloaded the MNIST data from Kaggle, which has preprocessed a subset of the data into a csv with a label column and 784 (28x28) greyscale pixel values.
I'm getting a ValueError: Shapes (None, 1) and (None, 10) are incompatible. I can't understand why.
Here's my code:
## load csv and partition into train/dev sets
dataframe = pd.read_csv('data/train.csv') ##load as pandas
dev_df = dataframe.sample(n=3000, random_state=1)
train_df = dataframe.drop(dev_df.index)
assert train_df.shape[1] == 785 #make sure it's not a problem with the data shape.
##Build the model
inputs = keras.Input(shape=(784))
x = layers.experimental.preprocessing.Rescaling(1./255)(inputs)
x = layers.Dense(100, activation='relu')(x)
x = layers.Dense(100, activation='relu')(x)
outputs = layers.Dense(10, activation='softmax')(x)
model = keras.Model(inputs=inputs,outputs=outputs)
model.summary()
At this point, I get the following model summary, which looks right to me (i.e., it looks a lot like what I'm seeing in the guides that I'm following.)
Model: "model_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_3 (InputLayer) [(None, 784)] 0
_________________________________________________________________
rescaling_6 (Rescaling) (None, 784) 0
_________________________________________________________________
dense_3 (Dense) (None, 100) 78500
_________________________________________________________________
dense_4 (Dense) (None, 100) 10100
_________________________________________________________________
dense_5 (Dense) (None, 10) 1010
=================================================================
Total params: 89,610
Trainable params: 89,610
Non-trainable params: 0
Then
## compile and fit model.
model.compile(optimizer="adam", loss="categorical_crossentropy")
(X, y) = (train_df.drop('label', axis=1).to_numpy(), train_df['label'].to_numpy())
assert X.shape[1] == 784 ## we're really sure this is the right size.
assert X.shape[0] == y.shape[0] ## the number of labels matches the number of samples
history = model.fit(X, y, epochs=1, batch_size=64)
The last line raises the error. I would guess it emerges with the final dense layer, since it has the expected (None,10) shape, but I can't figure out where the (None, 1) shaped entity (whatever it is) comes from.

ValueError: Input 0 of layer sequential_16 is incompatible with the layer: expected axis -1 of input shape to have value 24 but

I'm trying to do an image recognition using Keras on Flask. While doing prediction, I encounter this error
ValueError: Input 0 of layer sequential_16 is incompatible with the layer: expected axis -1 of input shape to have value 24 but received input with shape [None, 150, 150, 3]
I kinda understand the problem but I'm not sure how to specify the shape. This is on Flask server & I don't do any training here. I use a model that I have trained before on Jupyter notebook.
This is the code
def predict(img):
# Preprocess input image
img_width, img_height = 150, 150
x = load_img(img, target_size=(img_width, img_height))
x = img_to_array(x)
x = np.expand_dims(x, axis=0)
# Load model
dependencies = {
'precision': Precision,
'recall': Recall
}
model = load_model('model.h5', custom_objects=dependencies)
# Predict
result = model.predict(x)[0]
label = np.argmax(result)
return label
The traceback says it happens on result = model.predict(x)[0]. Anyone knows how to approach this error? Tried googling but I don't find any similar error.
EDIT - Model Summary
Model: "sequential_16"
Layer (type) Output Shape Param #
=================================================================
dense_96 (Dense) (None, 32) 800
_________________________________________________________________
dense_97 (Dense) (None, 1024) 33792
_________________________________________________________________
dense_98 (Dense) (None, 512) 524800
_________________________________________________________________
dense_99 (Dense) (None, 256) 131328
_________________________________________________________________
dense_100 (Dense) (None, 128) 32896
_________________________________________________________________
dense_101 (Dense) (None, 3) 387
_________________________________________________________________
activation_16 (Activation) (None, 3) 0
=================================================================
Total params: 724,003
Trainable params: 724,003
Non-trainable params: 0

Ok, so your input shape is wrong. The input layer isn't shown in the model summary but it says that the first layer has 800 parameters.
This tells me that your input layer has dimensions [None, 24] because 24 * 32 (weights) + 32 (biases) = 800.
When you add the first dense layer it should be
model.add(Dense(32, input_shape=(150,150,3))

Keras Conv1d Input Shape: Error when checking input

I am using keras with TF backend to build a simple Conv1d net. The data has the following shape:
train feature shape: (33960, 3053, 1)
train label shape: (33960, 686, 1)
I build my model with:
def create_conv_model():
inp = Input(shape=(3053, 1))
conv = Conv1D(filters=2, kernel_size=2)(inp)
pool = MaxPool1D(pool_size=2)(conv)
flat = Flatten()(pool)
dense = Dense(686)(flat)
model = Model(inp, dense)
model.compile(loss='mse', optimizer='adam')
return model
Model summary:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 3053, 1) 0
_________________________________________________________________
conv1d_1 (Conv1D) (None, 3052, 2) 6
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 1526, 2) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 3052) 0
_________________________________________________________________
dense_1 (Dense) (None, 686) 2094358
=================================================================
Total params: 2,094,364
Trainable params: 2,094,364
Non-trainable params: 0
Upon running
model.fit(x=train_feature,
y=train_label_categorical,
epochs=100,
batch_size=64,
validation_split=0.2,
validation_data=(test_feature,test_label_categorical),
callbacks=[tensorboard,reduce_lr,early_stopping])
i get the following VERY USUAL ERROR:
ValueError: Error when checking input: expected input_1 to have 3 dimensions, but got array with shape (8491, 3053)
I've checked pretty much all the posts regarding this very common problem, but I've been unable to find a solution. What am i doing wrong? I don't understand what's going on. Where is the shape (8491, 3053) coming from?
Any help will be much appreciated, I am not able to make this go away.

Change validation_data=(test_feature,test_label_categorical) in model.fit function to
validation_data=(np.expand_dims(test_feature, -1),test_label_categorical)
The model is expecting validation feature of shape (8491, 3053, 1), but in above code you are providing it (8491, 3053).

Could use help formatting data correctly for a Keras SimpleRNN

I'm struggling a bit getting data into the right format for a simpleRNN, or I'm struggling to define the model correctly. I'm hoping someone can spot the problem?
I'm trying to do classification of a list X of vectors of length 278 that contain integer values chosen from a dictionary vocab of length 9026 features as either belonging to class 0 or 1. Here's an example of my input data:
X=[[1,822,773,54,51,...],[2,3,1,41,3,...],[121,17,311,4,12,...],...]
y=[0,1,1,...]
So for example np.array(X).shape=(1000,278) and len(y)=1000
My model is:
model.add(L.InputLayer([None],dtype='int32'))
model.add(L.Embedding(input_dim=len(vocab)+1,\
output_dim=64,\
input_length=278))
model.add(L.SimpleRNN(64,return_sequences=True))
model.add(L.TimeDistributed(L.Dense(1,activation='softmax')))
model.compile(optimizer='adam',\
loss='categorical_crossentropy',\
metrics=['accuracy']
)
print(model.summary())
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_8 (Embedding) (None, 278, 64) 577728
_________________________________________________________________
simple_rnn_7 (SimpleRNN) (None, 278, 64) 8256
_________________________________________________________________
time_distributed_7 (TimeDist (None, 278, 1) 65
=================================================================
Total params: 586,049
Trainable params: 586,049
Non-trainable params: 0
_________________________________________________________________
None
I prepare them as follows:
X=np.array(X)
y=keras.utils.to_categorical(y)
frac=0.3
random_state=42
X_train,X_tmp,y_train,y_tmp = \
train_test_split(X,y,test_size=frac,random_state=random_state,\
stratify=y)
train=(X_train,y_train)
test=(X_tmp,y_tmp)
When I run the model:
model.fit(train[0],train[1],verbose=0,\
batch_size=batch_size,\
epochs=epochs,validation_data=test)
I get the following error:
ValueError: Error when checking target: expected time_distributed_1
to have 3 dimensions, but got array with shape (5450, 2)
If I change the input data to
train=(X_train,y_train[:,:,np.newaxis])
test=(X_tmp,y_tmp[:,:,np.newaxis])
and run the model, I get this error:
ValueError: Error when checking target: expected time_distributed_1
to have shape (278, 2) but got array with shape (2, 1)
OK so obviously I've got something wrong since my final dense layer is looking for shape 278 and not 2. So I tried this model without explicitly defining the input_length:
model.add(L.InputLayer([None],dtype='int32'))
model.add(L.Embedding(input_dim=len(vocab)+1,\
output_dim=64))
model.add(L.SimpleRNN(64,return_sequences=True))
model.add(L.TimeDistributed(L.Dense(1,activation='softmax')))
model.compile(optimizer='adam',\
loss='categorical_crossentropy',\
metrics=['accuracy']
)
print(model.summary())
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_10 (Embedding) (None, None, 64) 577728
_________________________________________________________________
simple_rnn_9 (SimpleRNN) (None, None, 64) 8256
_________________________________________________________________
time_distributed_9 (TimeDist (None, None, 2) 130
=================================================================
Total params: 586,114
Trainable params: 586,114
Non-trainable params: 0
and when I run the model, I get
ValueError: Error when checking target: expected time_distributed_9
to have shape (None, 2) but got array with shape (2, 1)
I'm very confused. Can anyone help me diagnose this?

Why are you using TimeDistributed? You don't need that at all. For each vector of length 278 you want to predict one and only one number which is between 0 and 1. Therefore the output shape of last layer should be (None,1). Remove the return_sequences argument of SimpleRNN layer as well.You don't need that as well. Like this:
model.add(L.SimpleRNN(64))
model.add(L.Dense(1,activation='sigmoid'))
Further, you should use 'sigmoid' as the activation function to make the last layer outputs a value between 0 and 1. And change the 'categorical_crossentropy' to 'binary_crossentropy'. You also don't need to convert the y to categorical. It is already zeros and ones and that's fine (just convert it to a numpy array); remember, you are doing binary classification here.
Plus, use the first model. Your second model does not make sense since you mentioned all of the input vectors are the same length (i.e. 278).
And one final point: remove that InputLayer. It is redundant. You are already setting the input shape in your embedding layer.