Related
in_dim, out_dim = 10, 7
bias = False
activation = None
layer = tfp.layers.weight_norm.WeightNorm(
tf.keras.layers.Dense(out_dim, input_shape=(None, in_dim, ),
use_bias = bias, activation = activation),
input_shape = (None, None, in_dim))
I would like to give a input with variable length in the second dimension.
Suppose I run the below code first.
input = tf.random.normal(shape = (2, 3, 10))
output = layer(input)
output.shape
# [2, 3, 7]
After running the above code, I give another input to network
input2 = tf.random.normal(shape = (2, 4, 10))
output2 = layer(input2)
However, it causes error
Input 0 of layer "weight_norm_3" is incompatible with the layer:
expected shape=(None, 3, 10), found shape=(2, 4, 10)
I would like to give a variable length of second dimension. How can I do it?
I am getting the following error:
Node: 'BGNet/dense/BiasAdd'
Matrix size-incompatible: In[0]: [1120,0], In[1]: [2048,1024]
[[{{node BGNet/dense/BiasAdd}}]] [Op:__inference_train_function_11676]
I found the root in this part of the model:
File "<ipython-input-14-3dcbdf5337b8>", line 69, in call
f = self.dense(f)
This is my custom multi model:
class BGNet(tf.keras.Model):
def __init__(self, img_h, img_w, img_c, batch_size, classes):
super(BGNet, self).__init__(name='BGNet')
self.img_h = img_h
self.img_w = img_w
self.img_c = img_c
self.batch_size = batch_size
self.classes = classes
# (224, 224, 3)
self.bgblock0 = BGBlock(f=[32, 32, 32, 32],
k=[7, 5, 5, 5],
d=[1, 2, 2, 1],
stage=0)
# (112, 112, 32)
self.bgblock1 = BGBlock(f=[64, 64, 64, 64],
k=[5, 5, 5, 3],
d=[2, 1, 1, 2],
stage=1)
# (56, 56, 64)
self.bgblock2 = BGBlock(f=[128, 128, 128, 128],
k=[5, 5, 3, 3],
d=[2, 1, 2, 1],
stage=2)
# (28, 28, 128)
self.bgblock3 = BGBlock(f=[256, 256, 256, 256],
k=[5, 3, 3, 3,],
d=[1, 2, 1, 2],
stage=3)
# (14, 14, 256)
self.bgblock4 = BGBlock(f=[512, 512, 512],
k=[3, 3, 3],
d=[1, 1, 2],
stage=4)
# (7, 7, 512)
self.bgblock5 = BGBlock(f=[1024, 1024, 1024],
k=[3, 3, 1],
d=[2, 1, 1],
stage=5)
# (4, 4, 1024)
self.bgblock6 = BGBlock(f=[2048, 2048],
k=[1, 1],
d=[1, 2],
stage=6)
# (2, 2, 2048)
self.flatten = tf.keras.layers.Flatten(name='flatten')
self.dense = tf.keras.layers.Dense(1024, activation='tanh', name='dense')
self.dropout = tf.keras.layers.Dropout(0.2, name='dropout')
self.prob = tf.keras.layers.Dense(1, activation='sigmoid', name='prob')
self.concat1 = tf.keras.layers.Concatenate(axis=-1, name='concat1')
self.bbox1 = tf.keras.layers.Dense(512, activation='relu', name='bbox1')
self.bbox2 = tf.keras.layers.Dropout(0.1, name='bbox2')
self.bbox3 = tf.keras.layers.Dense(256, activation='sigmoid', name='bbox3')
self.bbox = tf.keras.layers.Dense(4, name='bbox')
self.concat2 = tf.keras.layers.Concatenate(axis=-1, name='concat2')
self.cat = tf.keras.layers.Dense(len(self.classes), activation='softmax', name='cat')
def call(self, input_tensor, training=True):
x = self.bgblock0(input_tensor)
x = self.bgblock1(x)
x = self.bgblock2(x)
x = self.bgblock3(x)
x = self.bgblock4(x)
x = self.bgblock5(x)
x = self.bgblock6(x)
f = self.flatten(x)
f = self.dense(f)
f = self.dropout(f)
p = self.prob(f)
b = self.concat1([f, p])
b = self.bbox1(b)
b = self.bbox2(b)
b = self.bbox3(b)
b = self.bbox(b)
c = self.concat2([f, b])
c = self.cat(c)
return {'prob': p, 'bbox': b, 'class': c}
model1 = BGNet(H, W, C, B, N)
model1.build(input_shape=(B, H, W, C))
model1.call(tf.keras.layers.Input(shape=(H, W, C), batch_size=B))
model1.summary(print_fn=tf.print, expand_nested=True, show_trainable=True)
The custom (BGBlocks) blocks are not that important but if you are curious they are convolution blocks consisting of conv2d, batchnorm, activation and pooling layers
The model produces 3 outputs of different size vector while sharing the first dense layers. The output layers first predict the confidence score(prob in loss) of the an object being in the image. Next they predict the bounding box(bbox in loss) and finally the class(class in loss) of the bounded object.
The main issue is after the flatten layer. The model builds without errors with input images of (224, 224, 3). This is how the summary of the model looks: model.summary() image
I have even created a custom IOU (Intersection Over Union) for bounding boxes to be used as model metric. The losses are simple, inbuilt and as follows:
loss = {'prob': 'binary_crossentropy', 'bbox': 'mse', 'class': 'categorical_crossentropy'}
Hoe can I resolve this error?
I am trying to divide the mobilenetv2 model into 2 parts.
I first want to run the first part of the model, save the output, and feed it later on to the second model for certain reasons. I've tried code found here,
but I get the following error:
ValueError: A merge layer should be called on a list of inputs.
I think it is because the model isn't a Sequential.
Can someone help?
As I mentioned in my comments, some layers in mobile_net_v2 expect more than one inputs which are outputs of some other previous layers. Therefore adding them to a sequential model individually causes errors. I have an alternative solution for you. Using the mobile_net_v2 implementation (of my own) in this link, I was able to create the models you want:
import tensorflow as tf
from tensorflow.keras import layers, Model, Sequential
def conv_block(input_tensor, c, s, t, expand=True):
"""
Convolutional Block for mobile net v2
Args:
input_tensor (keras tensor): input tensor
c (int): output channels
s (int): stride size of first layer in the series
t (int): expansion factor
expand (bool): expand filters or not?
Returns: keras tensor
"""
first_conv_channels = input_tensor.get_shape()[-1]
if expand:
x = layers.Conv2D(
first_conv_channels*t,
1,
1,
padding='same',
use_bias=False
)(input_tensor)
x = layers.BatchNormalization()(x)
x = layers.ReLU(6.0)(x)
else:
x = input_tensor
x = layers.DepthwiseConv2D(
3,
s,
'same',
1,
use_bias=False
)(x)
x = layers.BatchNormalization()(x)
x = layers.ReLU(6.0)(x)
x = layers.Conv2D(
c,
1,
1,
padding='same',
use_bias=False
)(x)
x = layers.BatchNormalization()(x)
if input_tensor.get_shape() == x.get_shape() and s == 1:
return x+input_tensor
return x
def splitted_model(input_shape=(224,224,3)):
input = layers.Input(shape=input_shape)
x = layers.Conv2D(
32,
3,
2,
padding='same',
use_bias=False
)(input)
x = layers.BatchNormalization()(x)
x = layers.ReLU(6.0)(x)
x = conv_block(x, 16, 1, 1, expand=False)
x = conv_block(x, 24, 2, 6)
x = conv_block(x, 24, 1, 6)
x = conv_block(x, 32, 2, 6)
x = conv_block(x, 32, 1, 6)
x = conv_block(x, 32, 1, 6)
x = conv_block(x, 64, 2, 6)
x = conv_block(x, 64, 1, 6)
x = conv_block(x, 64, 1, 6)
x = conv_block(x, 64, 1, 6)
model_f = Model(inputs=input, outputs=x)
input_2 = layers.Input(shape=(x.shape[1:]))
x = conv_block(input_2, 96, 1, 6)
x = conv_block(x, 96, 1, 6)
x = conv_block(x, 96, 1, 6)
x = conv_block(x, 160, 2, 6)
x = conv_block(x, 160, 1, 6)
x = conv_block(x, 160, 1, 6)
x = conv_block(x, 320, 1, 6)
x = layers.Conv2D(
1280,
1,
1,
padding='same',
use_bias=False
)(x)
x = layers.BatchNormalization()(x)
x = layers.ReLU(6.0)(x)
x = layers.GlobalAveragePooling2D()(x)
model_h = Model(inputs=input_2, outputs=x)
return model_f, model_h
You could create your two models as such:
IMG_SIZE = 160
IMG_SHAPE = (IMG_SIZE, IMG_SIZE, 3)
model_f, model_h = splitted_model(input_shape=IMG_SHAPE)
Note that the weights are randomly initialized. If you want to have the weights from mobilenet_v2 trained on imagenet, you could run the following code to copy weights:
mobile_net = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
include_top=False,
weights='imagenet')
layer_f_counter = 0
layer_h_counter = 0
for i in range(len(mobile_net.layers)):
if layer_f_counter<len(model_f.layers):
if len(mobile_net.layers[i].get_weights()) > 0:
if len(model_f.layers[layer_f_counter].get_weights()) > 0:
print(mobile_net.layers[i].name,'here', model_f.layers[layer_f_counter].name, layer_f_counter)
model_f.layers[layer_f_counter].set_weights(mobile_net.layers[i].get_weights())
layer_f_counter += 1
print(layer_f_counter)
else:
if len(model_f.layers[layer_f_counter].get_weights()) > 0:
continue
else:
layer_f_counter+=1
else:
if layer_h_counter<len(model_h.layers):
if len(mobile_net.layers[i].get_weights()) > 0:
if len(model_h.layers[layer_h_counter].get_weights()) > 0:
print(mobile_net.layers[i].name,'here', model_h.layers[layer_h_counter].name, layer_h_counter)
model_h.layers[layer_h_counter].set_weights(mobile_net.layers[i].get_weights())
layer_h_counter += 1
print(layer_h_counter)
else:
if len(model_h.layers[layer_h_counter].get_weights()) > 0:
continue
else:
layer_h_counter+=1
It iterates through the layers of mobilenet_v2 loaded from Keras, it copies the weights of the first part to model_f, and the rest to model_h. You could check that the weights are correctly copied by print out some random layer weights from mobile_net and also the new models as follows:
print(model_f.layers[1].get_weights()) # printing weights of first conv layer in model_f
print(mobile_net.get_layer('Conv1').get_weights()) # printing weights of fist conv layer in mobile_net
Also for model_h:
print(model_h.layers[-4].get_weights()) # printing weights of last conv layer in model_h
print(mobile_net.get_layer('Conv_1').get_weights()) # printing weights of last conv layer in mobile_net
Note that I randomly selected which block to separate moile_net into model_f and model_h, you could edit it to change where you want to split. Hope it helps.
Just trying to use Keras but I am a bit confused about the Conv2D function when using padding=same. I wonder if someone can help me to figure out how p (padding) value is set when padding="same"?
Here is a code example:
# X.shape = (3, 2, 2, 2) at this point
X = Conv2D(filters=4, kernel_size=(2, 2), strides = (1, 1), padding = 'same',
name = 'apply_conv_2',
kernel_initializer = glorot_uniform())(X)
X = BatchNormalization(axis = 3, name = 'apply_bn_2')(X)
X = Activation('relu')(X)
# X.shape = (3, 2, 2, 4) at this point
You should read dimensions as (nr_samples, height, width, nr_channels)
If padding="same", height and width will remain the same. But I am a bit confused which value p takes here when calculating dimensions.
For instance, the dimension height should be calculated as:
height_next = ROUND_DOWN((( height_prev + 2xpadding - kernel_size ) / stride) + 1)
height_next = height_prev = 2.
And as seen above, kernel_size = 2 above. And stride = 1.
So..
2 = ROUND_DOWN(((2 + 2xpadding - 2) / 1) + 1)
If padding is 2, then the result becomes 5, which is not equal to 2.
If padding is 1, then result is 3 which is not equal to 2.
If padding is 0, then result is 1, which is not equal to 2.
I assume padding needs to be an integer value.
How does Keras calculate padding value here?
I am using the code below to create CNN layers.
conv1 = tf.layers.conv2d(inputs = input, filters = 20, kernel_size = [3,3],
padding = "same", activation = tf.nn.relu)
and I want to get the values of all kernels after training. It does not work it I simply do
kernels = conv1.kernel
So how should I retrieve the value of these kernels? I am also not sure what variables and method does conv2d has since tensorflow don't really tell it in conv2d class.
You can find all the variables in list returned by tf.global_variables() and easily lookup for variable you need.
If you wish to get these variables by name, declare a layer as:
conv_layer_1 = tf.layers.conv2d(activation=tf.nn.relu,
filters=10,
inputs=input_placeholder,
kernel_size=(3, 3),
name="conv1", # NOTE THE NAME
padding="same",
strides=(1, 1))
Recover the graph as:
gr = tf.get_default_graph()
Recover the kernel values as:
conv1_kernel_val = gr.get_tensor_by_name('conv1/kernel:0').eval()
Recover the bias values as:
conv1_bias_val = gr.get_tensor_by_name('conv1/bias:0').eval()
You mean you want to get the value of the weights for the conv1 layer.
You haven't actually defined the weights with conv2d, you need to do that. When I create a convolutional layer I use a function that performs all the necessary steps, here's a copy/paste of the function I use to create a each of my convolutional layers:
def _conv_layer(self, name, in_channels, filters, kernel, input_tensor, strides, dtype=tf.float32):
with tf.variable_scope(name):
w = tf.get_variable("w", shape=[kernel, kernel, in_channels, filters],
initializer=tf.contrib.layers.xavier_initializer_conv2d(), dtype=dtype)
b = tf.get_variable("b", shape=[filters], initializer=tf.constant_initializer(0.0), dtype=dtype)
c = tf.nn.conv2d(input_tensor, w, strides, padding='SAME', name=name + "c")
a = tf.nn.relu(c + b, name=name + "_a")
print name + "_a", a.get_shape().as_list(), name + "_w", w.get_shape().as_list(), \
"params", np.prod(w.get_shape().as_list()[1:]) + filters
return a, w.get_shape().as_list()
This is what I use to define 5 convolutional layers, this example is straight out of my code, so note that it's 5 convolutional layers stacked without using max pooling or anything, strides of 2 and 5x5 kernels.
conv1_a, _ = self._conv_layer("conv1", 3, 24, 5, self.imgs4d, [1, 2, 2, 1]) # 24.8 MiB/feature -> 540 x 960
conv2_a, _ = self._conv_layer("conv2", 24, 80, 5, conv1_a, [1, 2, 2, 1]) # 6.2 MiB -> 270 x 480
conv3_a, _ = self._conv_layer("conv3", 80, 256, 5, conv2_a, [1, 2, 2, 1]) # 1.5 MiB -> 135 x 240
conv4_a, _ = self._conv_layer("conv4", 256, 750, 5, conv3_a, [1, 2, 2, 1]) # 0.4 MiB -> 68 x 120
conv5_a, _ = self._conv_layer("conv5", 750, 2048, 5, conv4_a, [1, 2, 2, 1]) # 0.1 MiB -> 34 x 60
There's also a good tutorial on the tensorflow website on how to set up a convolutional network:
https://www.tensorflow.org/tutorials/deep_cnn
The direct answer to your question is that the weights for the convolutional layer are defined there as w, that's the tensor you're asking about if I understand you correctly.