Develop Reference

how to save and load custom siamese bert model

I am following this tutorial on how to train a siamese bert network:
https://keras.io/examples/nlp/semantic_similarity_with_bert/
all good, but I am not sure what is the best way to save the model after train it and save it.
any suggestion?
I was trying with
model.save('models/bert_siamese_v1')
which creates a folder with save_model.bp keras_metadata.bp and two subfolders (variables and assets)
then I try to load it with:
model.load_weights('models/bert_siamese_v1/')
and it gives me this error:
2022-03-08 14:11:52.567762: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open models/bert_siamese_v1/: Failed precondition: models/bert_siamese_v1; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?
what is the best way to proceed?

Try using tf.saved_model.save to save your model:
tf.saved_model.save(model, 'models/bert_siamese_v1')
model = tf.saved_model.load('models/bert_siamese_v1')
The warning you get during saving can apparently be ignored. After loading your model, you can use it for inference f(test_data):
f = model.signatures["serving_default"]
x1 = tf.random.uniform((1, 128), maxval=100, dtype=tf.int32)
x2 = tf.random.uniform((1, 128), maxval=100, dtype=tf.int32)
x3 = tf.random.uniform((1, 128), maxval=100, dtype=tf.int32)
print(f)
print(f(attention_masks = x1, input_ids = x2, token_type_ids = x3))
ConcreteFunction signature_wrapper(*, token_type_ids, attention_masks, input_ids)
Args:
attention_masks: int32 Tensor, shape=(None, 128)
input_ids: int32 Tensor, shape=(None, 128)
token_type_ids: int32 Tensor, shape=(None, 128)
Returns:
{'dense': <1>}
<1>: float32 Tensor, shape=(None, 3)
{'dense': <tf.Tensor: shape=(1, 3), dtype=float32, numpy=array([[0.40711606, 0.13456087, 0.45832306]], dtype=float32)>}

It seems you have two options
manually save weights
model.save_weights('./checkpoints/my_checkpoint')
model = create_model()
model.load_weights('./checkpoints/my_checkpoint')
save the entire model
Call model.save to save a model's architecture, weights, and training configuration in a single file/folder. This allows you to export a model so it can be used without access to the original Python code*. Since the optimizer-state is recovered, you can resume training from exactly where you left off.
Save model
# Create and train a new model instance.
model = create_model()
model.fit(train_images, train_labels, epochs=5)
# Save the entire model as a SavedModel.
!mkdir -p saved_model
model.save('saved_model/my_model')
load model
new_model = tf.keras.models.load_model('saved_model/my_model')
It seems that you are mixing both approaches, saving model and loading weights.

Cannot convert tf.keras.preprocessing.image_dataset_from_directory to np.array

I am trying to create a image classification model using CNN. For that I am reading the data using the tf.keras.preprocessing.image_dataset_from_directory function.
This is the code:
train_ds = tf.keras.preprocessing.image_dataset_from_directory(data_dir_train,seed=123,validation_split = 0.2,subset = 'training',image_size=(img_height, img_width),batch_size=batch_size)
Then I am trying to convert the dataset in np.array object. My code is
x_train = np.array(train_ds)
But when I print x_train, I am getting
array(<BatchDataset shapes: ((None, 180, 180, 3), (None,)), types: (tf.float32, tf.int32)>, dtype=object)
The object train_ds is of shape (2000,180,180,3). I am not sure what is wrong in my code.

When using image_dataset_from_directory:
... image_dataset_from_directory(main_directory, labels='inferred') will return a tf.data.Dataset that yields batches of images from the subdirectories ...
One option to get the data you want, is to use take to create a Dataset with at most count elements from this dataset.
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
img = np.empty((6000,180,180,3), dtype=np.float32)
label = np.empty((6000,), dtype=np.int32)
train_ds = tf.data.Dataset.from_tensor_slices((img,label)).batch(2000)
print(train_ds) # <BatchDataset shapes: ((None, 180, 180, 3), (None,)), types: (tf.float32, tf.int32)>
for imgs, labels in train_ds.take(1):
print(imgs.shape) # (2000, 180, 180, 3)
print(labels.shape) # (2000,)
for img in imgs:
plt.imshow(img.numpy().astype(np.uint8)) # print imgs in the batch
Depending on how you're structuring your code, you may not even need to convert to a numpy.array, since tf.keras.Model fit accepts tf.data datasets.
model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)

How can I change a tensor to NumPy?

I want to exchange Tensor a to a NumPy two-dimensional array for getting a heat map.
(Tensor(1, 64, 64, 1) -> numpy (64, 64))
I tried x.numpy(), but it doesn't work. The error message is this:
AttributeError: in user code: :187 call * x_np=x.numpy() /usr/local/lib/python3.7/dist packages/tensorflow/python/framework/ops.py:401 getattr self.getattribute(name) AttributeError: 'Tensor' object has no attribute 'numpy'
This is the tensor information and type of the tensor:
Tensor("ExpandDims:0", shape=(1, 64, 64, 1), dtype=float32)
<class 'tensorflow.python.framework.ops.Tensor'>
and I don't know what ExpandDims:0 means (what is this argv?).
Tensorflow:2.6.0
Numpy:1.21.2
I made the test code that has the same Tensor type, shape, and env, and it works.
What should I do?
import tensorflow as tf
import numpy
print(tf.__version__)
print(numpy.__version__)
a = tf.constant([[[[0.1]*1]*64]*64])
print(a)
print(a.numpy())

ds_train has shape (2, 224, 224, 3) instead of (None, 224, 224, 3)

I have created my own custom dataset (with 2 classes) with the following code:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
ds_train = tf.keras.preprocessing.image_dataset_from_directory(
'C:/Users/mydir/Source_Images/',
labels = 'inferred', # from subfolders in alphabetical order
label_mode = "int",
class_names = ["CVS", "No_CVS"],
color_mode = 'rgb',
batch_size = 2,
image_size = (224, 224),
shuffle = True, # randomized order of images
seed = 123, #set the seed if train, valid images are the same when you run again
validation_split = 0.1,
subset = "training"
)
df_train results in:
<BatchDataset shapes: ((None, 224, 224, 3), (None,)), types: (tf.float32, tf.int32)>
Now, I want to visualize my data by looking at 9 images:
for i, (image, label) in enumerate(ds_train.take(9)):
ax = plt.subplot(3, 3, i + 1)
plt.imshow(image.numpy().astype("uint8"))
plt.axis("off")
However, I get the following error:
line 61, in
plt.imshow(image.numpy().astype("uint8"))
TypeError: Invalid shape (2, 224, 224, 3) for image data
I'm looking for a way to resolve this, and be able to plot my images with matplotlib.
EDIT:
More importantly, it seems that the data of the data cannot be used when training the model either as I get this error:
ValueError: Input 0 is incompatible with layer EfficientNet: expected shape=(None, 224, 224, 3), found shape=(2, None, 224, 224, 3)
After running the Keras example code I found here (where I created ds_train with the image_dataset_from_directory instead of the tdsf.load() function).
So I think there is something going wrong in the way I created the ds_train. Any resolutions are very welcome.

It seems like you are leaving the batch_size in, when you do:
plt.imshow(image.numpy().astype("uint8"))
With your original code you still won't be able to see 9 images because of your batch_size. I think it will be fine if you do it like:
No errors should be thrown like TypeError: Invalid shape...:
plt.imshow(image[i].numpy().astype("uint8"))
Furthermore you can do following to see batch_size:
for img_batch_size, labels_batch_size in train_df:
print(img_batch_size.shape)
print(labels_batch_size.shape)
For your case img_batch_size.shape should print (2,224,224,3) where this tuple corresponds to image tensor.
For input_shape problem, you need to add your model so we can see what's wrong with input_shape.

reshape.cc:55 stretch_dim != -1. Node number X (RESHAPE) failed to prepare

I'm new to all this, and I need some help with running inference using a custom tflite yolov3 tiny model.
The error I am getting is:
File "/usr/local/lib/python3.6/dist-packages/tensorflow/lite/python/interpreter.py", line 524, in invoke
self._interpreter.Invoke()
RuntimeError: tensorflow/lite/kernels/reshape.cc:55 stretch_dim != -1 (0 != -1)Node number 35 (RESHAPE) failed to prepare.
What have I done to get here:
trained a custom yolov3 tiny model for object detection to detect just 1 class using this project
https://github.com/pythonlessons/TensorFlow-2.x-YOLOv3.git
used default hyperparameters:
https://github.com/pythonlessons/TensorFlow-2.x-YOLOv3/blob/master/yolov3/configs.py
used tf-nightly
the model is here:
https://github.com/vladimirhorvat/y/blob/master/app/src/main/assets/converted_model.tflite
When the model was trained I tested the SavedModel by running inference and it worked.
Converted the SavedModel to tflite, run inference on it using the following code, and received the error from the title:
interpreter = tf.lite.Interpreter(model_path="converted_model.tflite")
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
input_shape = input_details[0]['shape']
input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
interpreter.set_tensor(input_details[0]['index'], input_data)
interpreter.invoke()
(this code is from here, btw
https://www.tensorflow.org/lite/guide/inference#load_and_run_a_model_in_python )
Data for node 35:
type: Reshape
location: 35
inputs
data: name: functional_1/tf_op_layer_Tile_3/Tile_3;StatefulPartitionedCall/functional_1/tf_op_layer_Tile_3/Tile_3
shape: name: functional_1/tf_op_layer_strided_slice_6/strided_slice_6;StatefulPartitionedCall/functional_1/tf_op_layer_strided_slice_6/strided_slice_6
outputs
reshaped: name: functional_1/tf_op_layer_strided_slice_16/strided_slice_16;StatefulPartitionedCall/functional_1/tf_op_layer_strided_slice_16/strided_slice_16
Please help. I am out of ideas.

I was able to solve the exact same problem by following this similar post:
https://stackoverflow.com/a/62552677/11334316
In essence you would have to do the following when converting your model:
batch_size = 1
model = tf.keras.models.load_model('./yolo_model')
input_shape = model.inputs[0].shape.as_list()
input_shape[0] = batch_size
func = tf.function(model).get_concrete_function(tf.TensorSpec(input_shape, model.inputs[0].dtype))
model_converter = tf.lite.TFLiteConverter.from_concrete_functions([func])
model_lite = model_converter.convert()
f = open("./yolo_model.tflite", "wb")
f.write(model_lite)
f.close()