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?