I needed to increase the accuracy of a model. So I tried using TabNet.
I'm attaching the train & test data in a google drive link
Link: https://drive.google.com/drive/folders/1ronho26m9uX9_ooBTh0M81ox1a43ika8?usp=sharing
Here is my code.
import tensorflow as tf
import pandas as pd
# Load the train and test data into pandas dataframes
train_df = pd.read_csv("train.csv")
#train_df1 = pd.read_csv("train.csv")
test_df = pd.read_csv("test.csv")
# Split the target variable and the features
train_labels = train_df[[f'F_{i}' for i in range(40)]]
#train_labels=trai
test_labels = train_df.target
# Convert the dataframes to tensors
train_dataset = tf.data.Dataset.from_tensor_slices((train_df.values, train_labels.values))
test_dataset = tf.data.Dataset.from_tensor_slices((test_df.values, test_labels.values))
# Define the model using the TabNet architecture
model = tf.keras.models.Sequential([
tf.keras.layers.Input(shape=(train_df.shape[1],)),
tf.keras.layers.Dense(32, activation="relu"),
tf.keras.layers.Dense(64, activation="relu"),
tf.keras.layers.Dense(128, activation="relu"),
tf.keras.layers.Dense(1)
])
# Compile the model with a mean squared error loss function and the Adam optimizer
model.compile(loss="mean_squared_error", optimizer="adam")
# Train the model on the training data
model.fit(train_dataset.batch(32), epochs=5)
# Make predictions on the test data
predictions = model.predict(test_dataset.batch(32))
#predictions = model.predict(test_dataset)
# Evaluate the model on the test data
mse = tf.keras.losses.mean_squared_error(test_labels, predictions)
print("Mean Squared Error:", mse.numpy().mean())
I don't know what's wrong with it as I'm just a beginner.
Here is the error code:
ValueError Traceback (most recent call last)
<ipython-input-40-87712e1604a9> in <module>
24
25 # Make predictions on the test data
---> 26 predictions = model.predict(test_dataset.batch(32))
27 #predictions = model.predict(test_dataset)
28
1 frames
/usr/local/lib/python3.8/dist-packages/keras/engine/training.py in tf__predict_function(iterator)
13 try:
14 do_return = True
---> 15 retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
16 except:
17 do_return = False
ValueError: in user code:
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1845, in predict_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1834, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1823, in run_step **
outputs = model.predict_step(data)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1791, in predict_step
return self(x, training=False)
File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/usr/local/lib/python3.8/dist-packages/keras/engine/input_spec.py", line 264, in assert_input_compatibility
raise ValueError(f'Input {input_index} of layer "{layer_name}" is '
ValueError: Input 0 of layer "sequential_6" is incompatible with the layer: expected shape=(None, 42), found shape=(None, 41)
I didn't really know what to do. So I'm expecting help from you guys. Would be grateful to whatever tips you guys give.
Related
I am trying to build a machine learning model using pre-trained VGG16 with tensorflow, but I keep getting the same problem with the shape of the input. Compared to other public codes, the only difference is that I use a tf.data.dataset to share the data, instead of the DirectoryIterator of tf.image
Here is my code:
zip_ref = ZipFile(zip_file, 'r')
zip_ref.extractall(repository_dir)
zip_ref.close()
train_dir = os.path.join(repository_dir, "seg_train", "seg_train")
test_dir = os.path.join(repository_dir, "seg_test", "seg_test")
os.system(f"rm -r {os.path.join(repository_dir, 'seg_pred')}")
# load variables
validation_percentage = 0.2
label_mode = "int"
# for our model purposes
img_size = (224, 224)
color_mode='rgb'
data_train, data_val = image_dataset_from_directory(
train_dir,
batch_size=None,
label_mode=label_mode,
color_mode=color_mode,
image_size=img_size,
validation_split=validation_percentage,
subset="both",
seed=123,
)
data_test = image_dataset_from_directory(
test_dir,
batch_size=None,
label_mode=label_mode,
color_mode=color_mode,
image_size=img_size,
)
classes = data_train.class_names
print(classes)
scale = 1.0/255
normalization_layer = tf.keras.layers.Rescaling(scale)
data_train_norm = data_train.map(lambda x,y: (normalization_layer(x), y))
data_val_norm = data_val.map(lambda x,y: (normalization_layer(x), y))
data_test_norm = data_test.map(lambda x,y: (normalization_layer(x), y))
input_size = None
for img, label in data_train_norm.take(1).as_numpy_iterator():
input_size = img.shape
print(input_size)
base_model = VGG16(
input_shape=input_size, # Shape of our images
include_top = False, # Leave out the last fully connected layer
weights = 'imagenet'
)
# we do not train the parameters
for layer in base_model.layers:
layer.trainable = False
# Flatten the output layer to 1 dimension
x = layers.Flatten()(base_model.output)
# https://medium.com/analytics-vidhya/car-brand-classification-using-vgg16-transfer-learning-f219a0f09765
# FC layer very simple and with a softmax activation unit
x = layers.Dense(len(classes), activation="softmax")(x)
landscapeModel01 = Model(inputs=base_model.input, outputs=x, name="landscapeModel01")
loss = "sparse_categorical_crossentropy"
optimizer = "adam"
landscapeModel01.compile(
optimizer=optimizer,
loss=loss,
metrics=["loss","accuracy"]
)
#fit data
shuffle=True # variable
epochs=50 # variable, according if it is able to converge
batch_size = 200
print(landscapeModel01.input)
landscapeModel01.fit(
data_train_norm,
validation_data=data_val_norm,
epochs=epochs,
shuffle=shuffle,
batch_size=batch_size
)
and this is the error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In [10], line 8
4 batch_size = 200
6 print(landscapeModel01.input)
----> 8 landscapeModel01.fit(
9 data_train_norm,
10 validation_data=data_val_norm,
11 epochs=epochs,
12 shuffle=shuffle,
13 batch_size=batch_size
14 )
File ~/anaconda3/envs/faa/lib/python3.10/site-packages/keras/utils/traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
67 filtered_tb = _process_traceback_frames(e.__traceback__)
68 # To get the full stack trace, call:
69 # `tf.debugging.disable_traceback_filtering()`
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb
File /tmp/__autograph_generated_file8y_bf523.py:15, in outer_factory.<locals>.inner_factory.<locals>.tf__train_function(iterator)
13 try:
14 do_return = True
---> 15 retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
16 except:
17 do_return = False
ValueError: in user code:
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 1160, in train_function *
return step_function(self, iterator)
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 1146, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 1135, in run_step **
outputs = model.train_step(data)
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 993, in train_step
y_pred = self(x, training=True)
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/input_spec.py", line 295, in assert_input_compatibility
raise ValueError(
ValueError: Input 0 of layer "landscapeModel01" is incompatible with the layer: expected shape=(None, 224, 224, 3), found shape=(224, 224, 3)
What can I fix to make the code work?
versions:
tensorflow==2.10.0
#EDIT
I just found the solution: I was loading images with a batch size equals none, but the trained model demanded that the images had one, even if it was 1.
Solution
I just needed to load images in the image_dataset_from_directory with a batch_size parameter different from None. Considering my investigation did not consider data augmentation in the beginning, I chose 1.
I am using Keras and Tensorflow for the first time. I am trying to get vgg16 to train on the imagenette dataset.
Im not sure why I am getting an index out of range error. Maybe I am doing something obviously wrong. Ive been messing with this for awhile now so any help would be great!
Attached is the error and source code
I resized my images to the correct size based on the vgg16 documentation: https://keras.io/api/applications/vgg/#vgg16-function
`
tfds_name = 'imagenette'
(ds_train, ds_validation), ds_info= tfds.load(
name=tfds_name,
split=['train', 'validation'],
with_info = True,
as_supervised=True)
#model from assignment link https://keras.io/api/applications/vgg/#vgg16-function
ourModel = tf.keras.applications.VGG16(
include_top=True, #3 fill layers on top
weights="imagenet", #use imagenet
input_tensor=None, #use another layer as input
input_shape=None, #inly set if include to false
pooling=None, #use with include top false
classes=1000, #number of classes to set, we use imagenet values
classifier_activation="softmax", # classifier on input can only be none or softmax on pretrained
)
#make it so layers frozen
#for layer in ourModel.layers[:-1]:
# layer.trainable = False
loss_fn = tf.keras.losses.SparseCategoricalCrossentropy()
ourModel.compile(optimizer="adam",
loss=loss_fn,
metrics=['accuracy'])
def reshape(img,label):
img = tf.cast(img, tf.float32)
img = tf.image.resize(img, (224,224))
resize_image = tf.reshape(img, [-1, 224, 224, 3])
resize_image = preprocess_input(resize_image)
return resize_image, label
ds_train = ds_train.map(reshape)
ds_validation = ds_validation.map(reshape)
ourModel.fit(ds_train,
epochs=10,
validation_data = ds_validation)
`
Error:
ValueError: in user code:
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1051, in train_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1040, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1030, in run_step **
outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 890, in train_step
loss = self.compute_loss(x, y, y_pred, sample_weight)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 949, in compute_loss
y, y_pred, sample_weight, regularization_losses=self.losses)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 212, in __call__
batch_dim = tf.shape(y_t)[0]
ValueError: slice index 0 of dimension 0 out of bounds. for '{{node strided_slice}} = StridedSlice[Index=DT_INT32, T=DT_INT32, begin_mask=0, ellipsis_mask=0, end_mask=0, new_axis_mask=0, shrink_axis_mask=1](Shape, strided_slice/stack, strided_slice/stack_1, strided_slice/stack_2)' with input shapes: [0], [1], [1], [1] and with computed input tensors: input[1] = <0>, input[2] = <1>, input[3] = <1>.
Your reshape function is creating a single batch for the image data but not for label data. So return resize_image, label[None, ...] should fix the above bug.
But the right way to batch the train (and valid dataset) is to do: ds_train=ds_train.batch(BATCH_SIZE) and then removing tf.reshape(img, [-1, 224, 224, 3])
I am trying to build a binary Prediction model through Keras TensorFlow.
And I am having trouble when I add data augmentation inside.
This is my code.
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
train_dir = 'C:/train'
test_dir = 'C:/test'
train_data = train_datagen.flow_from_directory(train_dir,target_size=(224,224),class_mode='binary',seed=42)
test_data = test_datagen.flow_from_directory(test_dir,target_size=(224,224),class_mode='binary',seed=42)
tf.random.set_seed(42)
from tensorflow.keras.layers.experimental import preprocessing
data_augmentation = keras.Sequential([
preprocessing.RandomFlip("horizontal"),
preprocessing.RandomZoom(0.2),
preprocessing.RandomRotation(0.2),
preprocessing.RandomHeight(0.2),
preprocessing.RandomWidth(0.2),
], name='data_augmentation')
model_1 = tf.keras.Sequential([
tf.keras.layers.Input(shape=(224,224,3),name='input_layer'),
data_augmentation,
tf.keras.layers.Conv2D(20,3,activation='relu'),
tf.keras.layers.MaxPool2D(pool_size=2),
tf.keras.layers.Conv2D(20,3,activation='relu'),
tf.keras.layers.MaxPool2D(pool_size=2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(1,activation='sigmoid')
])
model_1.compile(loss=tf.keras.losses.binary_crossentropy,
optimizer='Adam',
metrics=['accuracy'])
model_1.fit(train_data,epochs=10,validation_data=test_data)
I ready tried this way but error again
inputs = tf.keras.layers.Input(shape=(224,224,3),name='input_layer')
x = data_augmentation(inputs)
x = tf.keras.layers.Conv2D(20,3,activation='relu')(x)
x = tf.keras.layers.Conv2D(20,3,activation='relu')(x)
x = tf.keras.layers.MaxPool2D(pool_size=2)(x)
x = tf.keras.layers.Flatten()(x)
outputs = tf.keras.layers.Dense(1,activation='sigmoid')(x)
model_1 = tf.keras.Model(inputs,outputs)
and this is error message:
Traceback (most recent call last):
File "C:/Users/pondy/PycharmProjects/pythonProject2/main.py", line 60, in <module>
model_1 = tf.keras.Sequential([
File "C:\Users\pondy\PycharmProjects\pythonProject2\venv\lib\site-packages\tensorflow\python\training\tracking\base.py", line 530, in _method_wrapper
result = method(self, *args, **kwargs)
File "C:\Users\pondy\PycharmProjects\pythonProject2\venv\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\pondy\PycharmProjects\pythonProject2\venv\lib\site-packages\keras\layers\core\dense.py", line 139, in build
raise ValueError('The last dimension of the inputs to a Dense layer '
ValueError: The last dimension of the inputs to a Dense layer should be defined. Found None. Full input shape received: (None, None)
Process finished with exit code 1
if didn't add data_augmentation inside it's not error
thank you for help<3
your code will work if you remove
preprocessing.RandomHeight(0.2),
preprocessing.RandomWidth(0.2),
I just started to learn Tensorflow and got an error. I watched a Neural Network Tutorial of Tech with Tim. I finished this episode and got a problem to the end. I couldn't predict the value. when i try it this error shows up:
Traceback (most recent call last):
File "C:/Users/havil/Documents/GitHub/Python/Machine-Learning-Tutorial/Neural Network Tutorial/Tutorial 2.py", line 56, in <module>
predict = model.predict([test_review])
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\tensorflow\python\framework\func_graph.py", line 1147, in autograph_handler
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\keras\engine\training.py", line 1801, in predict_function *
return step_function(self, iterator)
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\keras\engine\training.py", line 1790, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\keras\engine\training.py", line 1783, in run_step **
outputs = model.predict_step(data)
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\keras\engine\training.py", line 1751, in predict_step
return self(x, training=False)
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\havil\anaconda3\envs\tf_3.7\lib\site-packages\keras\engine\input_spec.py", line 214, in assert_input_compatibility
raise ValueError(f'Input {input_index} of layer "{layer_name}" '
ValueError: Exception encountered when calling layer "sequential" (type Sequential).
Input 0 of layer "global_average_pooling1d" is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 16)
Call arguments received:
• inputs=('tf.Tensor(shape=(None,), dtype=int32)',)
• training=False
• mask=None
My whole code looks like this:
import tensorflow as tf
from tensorflow import keras
import numpy as np
data = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = data.load_data(num_words=10000)
print(train_data[0])
# decode Data
word_index = data.get_word_index()
word_index = {key: (value+3) for key, value in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2
word_index["<UNUSED>"] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
train_data = keras.preprocessing.sequence.pad_sequences(train_data, value=word_index["<PAD>"], padding="post", maxlen=250)
test_data = keras.preprocessing.sequence.pad_sequences(test_data, value=word_index["<PAD>"], padding="post", maxlen=250)
def decode_review(text):
return " ".join([reverse_word_index.get(i, "?") for i in text])
print(decode_review(test_data[0]))
model = keras.Sequential()
model.add(keras.layers.Embedding(10000, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation="relu"))
model.add(keras.layers.Dense(1, activation="sigmoid"))
model.summary()
model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
x_val = train_data[:10000]
x_train = train_data[10000:]
y_val = train_labels[:10000]
y_train = train_labels[10000:]
fitModel = model.fit(x_train, y_train, epochs=40, batch_size=512, validation_data=(x_val, y_val), verbose=1)
results = model.evaluate(test_data, test_labels)
print(results)
test_review = test_data[0]
predict = model.predict([test_review])
print("Review: ")
print(decode_review(test_review))
print("Prediction: " + str(predict[0]))
print("Actual: " + str(test_labels[0]))
print(results)
Does anyone have an idea how to fix this error?
I could solve this problem. model.predict doesn´t accept normal Lists. I just replaced it with an Numpy array.
test_review = test_data[0]
prediction = model.predict(np.array([test_review]))
print("Review: " + decode_review(test_review))
print("Prediction: " + str(prediction[0]))
print("Actual: " + str(test_labels[0]))
I have same issue, but i noticed that prediction does not work just for a single input, if you do the same with with all of the test data it works fine
prediction = model.predict(test_data)
for i in range(10):
print("Review", test_data[i])
print("Decoded: ", decode_review(test_data[i]))
print("Actual: ", str(test_labels[i]))
print("Predicted: ", str(prediction[i]))
It probably won't help you but i hope it does because i'm struggling with this all day long and really want to know how to fix it
I had the same issue but I solved it by appending the test sample to an empty list then predicting it from there and it worked
I am very new in using TF. I would like build a model with 6 input and 1 output. My code is available below.
import tensorflow as tf
import numpy as np
import pandas as pd
from tensorflow.keras import layers
import matplotlib.pyplot as plt
abalone_train = pd.read_csv("sipm2.csv",
names=["Hit1", "Time1", "Hit2", "Time2", "Hit3",
"Time3", "PosX"])
abalone_train.head()
abalone_features = abalone_train.copy()
abalone_labels = abalone_features.pop('PosX')
abalone_features = np.array(abalone_features)
print(abalone_features)
abalone_model = tf.keras.Sequential([
layers.Dense(64),
layers.Dense(64)
])
abalone_model.compile(loss='mean_squared_error', optimizer=tf.keras.optimizers.Adam(0.1), metrics=['mean_squared_error'])
history = abalone_model.fit(abalone_features, abalone_labels, epochs=100)
abalone_model.summary()
print("Finished training the model")
#plt.xlabel('Epoch Number')
#plt.ylabel("Loss Magnitude")
#plt.plot(history.history['loss'])
#plt.show()
posx_prediction = abalone_model.predict([75., 1., 75. ,1.3 ,66. ,2.])
print(posx_prediction)
The error I got is:
WARNING:tensorflow:Model was constructed with shape (None, 6) for input KerasTensor(type_spec=TensorSpec(shape=(None, 6), dtype=tf.float32, name='dense_input'), name='dense_input', description="created by layer 'dense_input'"), but it was called on an input with incompatible shape (None,).
Traceback (most recent call last):
File "/Users/sertac/Work/TensorFlow/test3.py", line 39, in <module>
posx_prediction = abalone_model.predict([75., 1., 75. ,1.3 ,66. ,2.])
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/tensorflow/python/framework/func_graph.py", line 1147, in autograph_handler
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/keras/engine/training.py", line 1801, in predict_function *
return step_function(self, iterator)
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/keras/engine/training.py", line 1790, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/keras/engine/training.py", line 1783, in run_step **
outputs = model.predict_step(data)
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/keras/engine/training.py", line 1751, in predict_step
return self(x, training=False)
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/Users/sertac/Library/Python/3.9/lib/python/site-packages/keras/engine/input_spec.py", line 228, in assert_input_compatibility
raise ValueError(f'Input {input_index} of layer "{layer_name}" '
ValueError: Exception encountered when calling layer "sequential" (type Sequential).
Input 0 of layer "dense" is incompatible with the layer: expected min_ndim=2, found ndim=1. Full shape received: (None,)
Call arguments received:
• inputs=tf.Tensor(shape=(None,), dtype=float32)
• training=False
• mask=None
I would like appreciate if you could help me how to get prediction?
Thanks in advance.
Sipm2.csv
104.241,1.12209,67.51,1.30428,57.354,1.48099,3.9
104.796,1.12425,67.787,1.3103,58.31,1.47481,3.5
103.203,1.10605,67.039,1.29599,56.825,1.47089,3.0
84.857,1.12028,80.898,1.23234,62.08,1.39148,2.5
86.015,1.16361,80.656,1.20233,62.945,1.37363,1.5
83.987,1.20226,80.211,1.17464,62.002,1.36756,1.0
85.35,1.21761,81.777,1.15021,62.541,1.34058,0.5
For 6 input and 1 output, your model should look something like below.
abalone_model = tf.keras.Sequential([
tf.keras.Input(shape=(6,))
layers.Dense(64),
layers.Dense(1, activation='softmax')
])