I have successfully converted a quantized 8bit tflite model for object detection. My model was originally trained on images that are normalized by dividing 255 so the original input range is [0, 1]. Since my quantized tflite model requires input to be uint8, how can I convert my image (originally [0, 255]) to be correct for my network?
Also how can I convert output to float to compare the results with floating point model?
The following code does not give me the right result.
'''python
im = cv2.imread(image_path)
im = im.astype(np.float32, copy=False)
input_image = im
input_image = np.array(input_image, dtype=np.uint8)
input_image = np.expand_dims(input_image, axis=0)
interpreter.set_tensor(input_details[0]['index'], input_image)
interpreter.invoke()
output_data = interpreter.get_tensor(output_details[0]['index'])
output_data2 = interpreter.get_tensor(output_details[1]['index'])
output_data3 = interpreter.get_tensor(output_details[2]['index'])
min_1 = -8.198164939880371
max_1 = 8.798029899597168
scale = (max_1 - min_1)/ 255.0
min_2 = -9.77856159210205
max_2 = 10.169703483581543
scale_2 = (max_2 - min_2) / 255.0
min_3 = -14.382895469665527
max_3 = 11.445544242858887
scale_3 = (max_3 - min_3) / 255.0
output_data = (output_data ) * scale + min_1
output_data2 = (output_data2) * scale_2 + min_2
output_data3 = (output_data3) * scale_3 + min_3
'''
i met the same problem but in pose estimation.
have you solved the problem yet?
you use quantized aware training?
i think you can get a q and z value(because you have to give mean and std-err when you use tflite api or toco commonad to get a quantized 8bit tflite model) about your input image.
try these codes:
image = q_input* (image - z_input)
output_data = q_output(image - z_output)
etc.
(for different layers you can access different q and z)
Let me know if you tried this way
I've converted the image via OpenCV to "CV_8UC3" and this worked for me:
// Convert to RGB color space
if (image.channels() == 1) {
cv::cvtColor(image, image, cv::COLOR_GRAY2RGB);
} else {
cv::cvtColor(image, image, cv::COLOR_BGR2RGB);
}
image.convertTo(image, CV_8UC3);
Related
I am using this function to predict the output of never seen images
def predictor(img, model):
image = cv2.imread(img)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, (224, 224))
image = np.array(image, dtype = 'float32')/255.0
plt.imshow(image)
image = image.reshape(1, 224,224,3)
clas = model.predict(image).argmax()
name = dict_class[clas]
print('The given image is of \nClass: {0} \nSpecies: {1}'.format(clas, name))
how to change it, if I want the top 2(or k) accuracy
i.e
70% chance its dog
15% its a bear
If you are using TensorFlow + Keras and probably doing multi-class classification, then the output of model.predict() is a tensor representing either the logits or already the probabilities (softmax on top of logits).
I am taking this example from here and slightly modifying it : https://www.tensorflow.org/api_docs/python/tf/math/top_k.
#See the softmax, probabilities add up to 1
network_predictions = [0.7,0.2,0.05,0.05]
prediction_probabilities = tf.math.top_k(network_predictions, k=2)
top_2_scores = prediction_probabilities.values.numpy()
dict_class_entries = prediction_probabilities.indices.numpy()
And here in dict_class_entries you have then the indices (sorted ascendingly) in accordance with the probabilities. (i.e. dict_class_entries[0] = 0 (corresponds to 0.7) and top_2_scores[0] = 0.7 etc.).
You just need to replace network_probabilities with model.predict(image).
Notice I removed the argmax() in order to send an array of probabilities instead of the index of the max score/probability position (that is, argmax()).
I want to concatenate three images with size [1024,1024,3] to make a batch with size [3,1024,1024,3]. I wrote this code with TensorFlow but it doesn't work. It returns the error "InaccessibleTensorError: The tensor 'Tensor("truediv:0", shape=(1024, 1024, 3), dtype=float32)' cannot be accessed here: it is defined in another function or code block. Use return values, explicit Python locals or TensorFlow collections to access it.".
def decode_img(filename):
image = tf.ones((3,1024,1024,3),dtype=tf.dtypes.float32)
cnt=0
slices = []
for fi in filename:
bits = tf.io.read_file(fi)
img = tf.image.decode_jpeg(bits, channels=3)
img = tf.image.resize(img, (1024,1024))
slices.append(tf.cast(img, tf.float32) / 255.0)
cnt +=1
image = tf.stack(slices)
return image
#-----------------------
filenames = ['img1.png', 'img2.png', 'img3.png']
dataset = tf.data.Dataset.from_tensor_slices(filenames)
dataset = dataset.map(decode_img, num_parallel_calls=AUTO)
In general, tensorflow does not support item assignment. Rather, generate all the img layers you want and then use tf.stack() or tf.concatenate.
filename = [img1.png, img2.png, img3.png]
cnt=0
slices = []
for fi in filename:
bits = tf.io.read_file(fi)
img = tf.image.decode_jpeg(bits, channels=3)
img = tf.image.resize(img, (1024,1024))
slices.append(tf.cast(img, tf.float32) / 255.0)
cnt +=1
image = tf.stack(slices)
General Explanation:
My codes work fine, but the results are wired. I don't know the problem is with
the network structure,
or the way I feed the data to the network,
or anything else.
I am struggling with this error several weeks and so far I have changed the loss function, optimizer, data generator, etc., but I could not solve it. I appreciate any help.
If the following information is not enough, let me know, please.
Field of study:
I am using tensorflow, keras for multiclass classification. The dataset has 36 binary human attributes. I have used resnet50, then for each part of the body (head, upper body, lower body, shoes, accessories), I have added a separated branch to the network. The network has 1 input image with 36 labels and 36 output nodes (36 denes layers with sigmoid activation).
Problem:
The problem is that the accuracy that keras is reporting is high, but f1-score is very low or zero for most of the outputs (even when I use f1-score as a metric when compiling the network, the f1-socre for validation is very bad).
aAfter train, when I use the network in prediction mode, it returns always one/zero for some classes. It means that the network is not able to learn (even when I use weighted loss function or focal loss function.)
Why it is weird? Because, state-of-the-art methods report heigh f1 score even after the first epoch (e.g. https://github.com/chufengt/iccv19_attribute, that I have run it in my PC and got good results after one epoch).
Parts of the Codes:
print("setup model ...")
input_image = KL.Input(args.img_input_shape, name= "input_1")
C1, C2, C3, C4, C5 = resnet_graph(input_image, architecture="resnet50", stage5=False, train_bn=True)
output_layers = merged_model (input_features=C4)
model = Model(inputs=input_image, outputs=output_layers, name='SoftBiometrics_Model')
...
print("model compiling ...")
OPTIM = optimizers.Adadelta(lr=args.learning_rate, rho=0.95)
model.compile(optimizer=OPTIM, loss=binary_focal_loss(alpha=.25, gamma=2), metrics=['acc',get_f1])
plot_model(model, to_file='model.png')
...
img_datagen = ImageDataGenerator(rotation_range=6, width_shift_range=0.03, height_shift_range=0.03, brightness_range=[0.85,1.15], shear_range=0.06, zoom_range=0.09, horizontal_flip=True, preprocessing_function=preprocess_input_resnet, rescale=1/255.)
img_datagen_test = ImageDataGenerator(preprocessing_function=preprocess_input_resnet, rescale=1/255.)
def multiple_outputs(generator, dataframe, batch_size, x_col):
Gen = generator.flow_from_dataframe(dataframe=dataframe,
directory=None,
x_col = x_col,
y_col = args.Categories,
target_size = (args.img_input_shape[0],args.img_input_shape[1]),
class_mode = "multi_output",
classes=None,
batch_size = batch_size,
shuffle = True)
while True:
gnext = Gen.next()
# return image batch and 36 sets of lables
labels = gnext[1]
output_dict = {"{}_output".format(Category): np.array(labels[index]) for index, Category in enumerate(args.Categories)}
yield {'input_1':gnext[0]}, output_dict
trainGen = multiple_outputs (generator = img_datagen, dataframe=Train_df_img, batch_size=args.BATCH_SIZE, x_col="Train_Filenames")
testGen = multiple_outputs (generator = img_datagen_test, dataframe=Test_df_img, batch_size=args.BATCH_SIZE, x_col="Test_Filenames")
STEP_SIZE_TRAIN = len(Train_df_img["Train_Filenames"]) // args.BATCH_SIZE
STEP_SIZE_VALID = len(Test_df_img["Test_Filenames"]) // args.BATCH_SIZE
...
print("Fitting the model to the data ...")
history = model.fit_generator(generator=trainGen,
epochs=args.Number_of_epochs,
steps_per_epoch=STEP_SIZE_TRAIN,
validation_data=testGen,
validation_steps=STEP_SIZE_VALID,
callbacks= [chekpont],
verbose=1)
There is a possibility that you are passing binary f1-score to compile function. This should fix the problem -
pip install tensorflow-addons
...
import tensorflow_addons as tfa
f1 = tfa.metrics.F1Score(36,'micro' or 'macro')
model.compile(...,metrics=[f1])
You can read more about how f1-micro and f1-macro is calculated and which can be useful here.
Somehow, the predict_generator() of Keras' model does not work as expected. I would rather loop through all test images one-by-one and get the prediction for each image in each iteration. I am using Plaid-ML Keras as my backend and to get prediction I am using the following code.
import os
from PIL import Image
import keras
import numpy
print("Prediction result:")
dir = "/path/to/test/images"
files = os.listdir(dir)
correct = 0
total = 0
#dictionary to label all traffic signs class.
classes = {
0:'This is Cat',
1:'This is Dog',
}
for file_name in files:
total += 1
image = Image.open(dir + "/" + file_name).convert('RGB')
image = image.resize((100,100))
image = numpy.expand_dims(image, axis=0)
image = numpy.array(image)
image = image/255
pred = model.predict_classes([image])[0]
sign = classes[pred]
if ("cat" in file_name) and ("cat" in sign):
print(correct,". ", file_name, sign)
correct+=1
elif ("dog" in file_name) and ("dog" in sign):
print(correct,". ", file_name, sign)
correct+=1
print("accuracy: ", (correct/total))
I have an equation that describes a curve in two dimensions. This equation has 5 variables. How do I discover the values of them with keras/tensorflow for a set of data? Is it possible? Someone know a tutorial of something similar?
I generated some data to train the network that has the format:
sample => [150, 66, 2] 150 sets with 66*2 with the data something like "time" x "acceleration"
targets => [150, 5] 150 sets with 5 variable numbers.
Obs: I know the range of the variables. I know too, that 150 sets of data are too few sample, but I need, after the code work, to train a new network with experimental data, and this is limited too. Visually, the curve is simple, it has a descendent linear part at the beggining and at the end it gets down "like an exponential".
My code is as follows:
def build_model():
model = models.Sequential()
model.add(layers.Dense(512, activation='relu', input_shape=(66*2,)))
model.add(layers.Dense(5, activation='softmax'))
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['mae'])
return model
def smooth_curve(points, factor=0.9):
[...]
return smoothed_points
#load the generated data
train_data = np.load('samples00.npy')
test_data = np.load('samples00.npy')
train_targets = np.load('labels00.npy')
test_targets = np.load('labels00.npy')
#normalizing the data
mean = train_data.mean()
train_data -= mean
std = train_data.std()
train_data /= std
test_data -= mean
test_data /= std
#k-fold validation:
k = 3
num_val_samples = len(train_data)//k
num_epochs = 100
all_mae_histories = []
for i in range(k):
val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
val_targets = train_targets[i * num_val_samples: (i + 1) * num_val_samples]
partial_train_data = np.concatenate(
[train_data[:i * num_val_samples],
train_data[(i + 1) * num_val_samples:]],
axis=0)
partial_train_targets = np.concatenate(
[train_targets[:i * num_val_samples],
train_targets[(i + 1) * num_val_samples:]],
axis=0)
model = build_model()
#reshape the data to get the format (100, 66*2)
partial_train_data = partial_train_data.reshape(100, 66 * 2)
val_data = val_data.reshape(50, 66 * 2)
history = model.fit(partial_train_data,
partial_train_targets,
validation_data = (val_data, val_targets),
epochs = num_epochs,
batch_size = 1,
verbose = 1)
mae_history = history.history['val_mean_absolute_error']
all_mae_histories.append(mae_history)
average_mae_history = [
np.mean([x[i] for x in all_mae_histories]) for i in range(num_epochs)]
smooth_mae_history = smooth_curve(average_mae_history[10:])
plt.plot(range(1, len(smooth_mae_history) + 1), smooth_mae_history)
plt.xlabel('Epochs')
plt.ylabel('Validation MAE')
plt.show()
Obviously as it is, I need to get the best accuracy possible, but I am getting an "median absolute error(MAE)" like 96%, and this is inaceptable.
I see some basic bugs in this methodology. Your final layer of the network has a softmax layer. This would mean it would output 5 values, which sum to 1, and behave as a probability distribution. What you actually want to predict is true numbers, or rather floating point values (under some fixed precision arithmetic).
If you have a range, then probably using a sigmoid and rescaling the final layer would to match the range (just multiply with the max value) would help you. By default sigmoid would ensure you get 5 numbers between 0 and 1.
The other thing should be to remove the cross entropy loss and use a loss like RMS, so that you predict your numbers well. You could also used 1D convolutions instead of using Fully connected layers.
There has been some work here: https://julialang.org/blog/2017/10/gsoc-NeuralNetDiffEq which tries to solve DEs and might be relevant to your work.
I'm trying to train a gif dataset but am getting this error.
It says the error is probably because of the ResizeBilinear
This is the code for the resize bilinear
input_height, input_width = hub.get_expected_image_size(module_spec)
input_depth = hub.get_num_image_channels(module_spec)
gif_data = tf.placeholder(tf.string, name='DecodeGIFInput')
decoded_image = tf.image.decode_image(gif_data, channels=None,
dtype=tf.uint8, name=None)
# Convert from full range of uint8 to range [0,1] of float32.
decoded_image_as_float = tf.image.convert_image_dtype(decoded_image,
tf.float32)
decoded_image_4d = tf.expand_dims(decoded_image_as_float, 0)
resize_shape = tf.stack([input_height, input_width])
resize_shape_as_int = tf.cast(resize_shape, dtype=tf.int32)
resized_image = tf.image.resize_bilinear(decoded_image_4d,
resize_shape_as_int)
return gif_data, resized_image
This is the link to the github of the full file.
Link to github retrain.py
I am assuming that the list in your title corresponds to [?,batch_size,height,width,channels]. If so, and assuming that you do not need the first dimension ([1]), you can replace
resized_image = tf.image.resize_bilinear(decoded_image_4d,resize_shape_as_int)
with
squeezed_image = tf.squeeze(decoded_image_4d,0)
resized_image = tf.image.resize_bilinear(squeezed_image,resize_shape_as_int)
tf.squeeze will eliminate the first dimension (corresponding to axis 0) and this should stop the error from popping up