A bug in transition layer

Question

A bug in transition layer

NatalieZou opened this issue 6 years ago · 29 comments

the original filter in transition_layer is equal to the growth_k, which is too small ,so the result is not good ,and the network is hard to converge , so I change it as below , referring to another code , and the result is normal now and much more better.
def transition_layer(self, x, scope):
with tf.name_scope(scope):
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
shape = x.get_shape().as_list()
in_channel = shape[3]
#x = conv_layer(x, filter=self.filters, kernel=[1,1], layer_name=scope+'_conv1')
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
x = Drop_out(x, rate=dropout_rate, training=self.training)
x = Average_pooling(x, pool_size=[2,2], stride=2)

Answer 1 · 2018-05-11T14:16:03.000Z

Hi NatalieZou I didn't notice that, I will use it and see the the results, could we open a discussion about this code here?

Answer 2 · 2018-05-11T21:48:48.000Z

NatalieZou could you please post your training loss curve here after fixing that bug?

Answer 3 · 2018-05-12T03:15:00.000Z

thank you for your information ,i will change the parameter, and try it again.

Answer 4 · 2018-05-14T03:26:09.000Z

@Abdelpakey ok, of course you can. This is my training acc and loss curve:

Answer 5 · 2018-05-15T04:44:09.000Z

@NatalieZou thank you for your post, can you tell me about the K and L, dropout rate, etc values of your loss curve?

Answer 6 · 2018-09-09T11:45:30.000Z

@GyuminDev In original paper, there is a hyper-parameter called compression factor. This factor is used to decimate the tensor which is feed from a dense block to a transition layer. In my opinion, you can try the K and L values mentioned in paper. The problem in this issue is not so related to these two values. Good luck, hope your model works well.

Answer 7 · 2019-03-04T03:29:32.000Z

Yes, I meet this problem too. Thank you.

Answer 8 · 2019-03-04T03:46:43.000Z

@Abdelpakey ok, of course you can. This is my training acc and loss curve:

How many densenet blocks do you use? How about the depth and growth rate?

Answer 9 · 2019-03-04T07:39:50.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Answer 10 · 2019-03-04T07:58:34.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

Answer 11 · 2019-03-04T08:07:33.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

Answer 12 · 2019-03-04T08:10:16.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

Answer 13 · 2019-03-04T08:17:31.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

I used MomentumOptimizer and the init_learning_rate is 1e-1

Answer 14 · 2019-03-04T08:37:24.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

I used MomentumOptimizer and the init_learning_rate is 1e-1

Could you please send me a copy of your training script?
I really don't know why.

Answer 15 · 2019-03-04T08:49:11.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

I used MomentumOptimizer and the init_learning_rate is 1e-1

I see that your training acc can reach 90% in less than 10 epochs. The test acc also reaches 85% in 10 epochs. This is far beyond the results on my computer.

Answer 16 · 2019-03-04T08:59:18.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

I used MomentumOptimizer and the init_learning_rate is 1e-1

I see that your training acc can reach 90% in less than 10 epochs. The test acc also reaches 85% in 10 epochs. This is far beyond the results on my computer.

Could you give me your email, the .py file can't be send in github

Answer 17 · 2019-03-04T09:04:46.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

I used MomentumOptimizer and the init_learning_rate is 1e-1

I see that your training acc can reach 90% in less than 10 epochs. The test acc also reaches 85% in 10 epochs. This is far beyond the results on my computer.

Could you give me your email, the .py file can't be send in github

my email is yuffonzhang@163.com
Thanks a lot.
The acc really sucks on my computer.

Answer 18 · 2019-03-04T09:05:35.000Z

@NatalieZou As you said, I fixed the code.
@yuffon Please check.

Answer 19 · 2019-03-06T01:15:21.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

I used MomentumOptimizer and the init_learning_rate is 1e-1

I see that your training acc can reach 90% in less than 10 epochs. The test acc also reaches 85% in 10 epochs. This is far beyond the results on my computer.

Could you give me your email, the .py file can't be send in github

my email is yuffonzhang@163.com
Thanks a lot.
The acc really sucks on my computer.

thank you.
I have tried deep densenet on my computer.
It reaches 93.78%.
But when I use densenet40-12, the acc is not good.
Have you tried some shallower densenet(such as densenet40-12)?

Answer 20 · 2019-03-07T02:43:17.000Z

@NatalieZou As you said, I fixed the code.
@yuffon Please check.

Thank you very much.
I checked the data processing code.
The standardization is performed on the total data set.
np.mean(x_train[:, :, :, 0]) computes the mean of the first channel of the whole data set.
I have tried per image standardization using tf.dataset API, the acc cannot reach 91%.
Why?

Answer 21 · 2019-03-07T08:56:20.000Z

@NatalieZou @taki0112
When I use this code, the program is reported as follows:

Traceback (most recent call last):
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 184, in
logits = DenseNet(x=batch_images, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 84, in init
self.model = self.Dense_net(x)
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 146, in Dense_net
x = self.transition_layer(x, scope='trans_'+str(i))
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 113, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

I think this may be that in_channel is not an integer after 0.5.
When I change it to
x = conv_layer(x, filter=in_channel1, kernel=[1,1], layer_name=scope+'_conv1'),
the network can run.

Then I use
Print(x)
Print(in_channel) to check their size。
I found that x and in_channel have two values.
Tensor("trans_0/Relu:0", shape=(?, 6, 6, 72), dtype=float32)
72
Tensor("trans_1/Relu:0", shape=(?, 3, 3, 120), dtype=float32)
120

From the above it seems that *0.5 should also be satisfied, and x and in_channel should also have only one value?
I want to know why this problem happened？

Answer 22 · 2019-04-23T08:09:58.000Z

@NatalieZou @taki0112
When I use this code, the program is reported as follows:

Traceback (most recent call last):
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 184, in
logits = DenseNet(x=batch_images, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 84, in init
self.model = self.Dense_net(x)
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 146, in Dense_net
x = self.transition_layer(x, scope='trans_'+str(i))
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 113, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

I think this may be that in_channel is not an integer after _0.5. When I change it to x = conv_layer(x, filter=in_channel_1, kernel=[1,1], layer_name=scope+'_conv1'),
the network can run.

Then I use
Print(x)
Print(in_channel) to check their size。
I found that x and in_channel have two values.
Tensor("trans_0/Relu:0", shape=(?, 6, 6, 72), dtype=float32)
72
Tensor("trans_1/Relu:0", shape=(?, 3, 3, 120), dtype=float32)
120

From the above it seems that *0.5 should also be satisfied, and x and in_channel should also have only one value?
I want to know why this problem happened？

yes,I also have this problem, I run Dense_Cifar10.py, The program reports as follow：
Traceback (most recent call last):
File "Densenet_Cifar10.py", line 221, in
logits = DenseNet(x=input_x, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "Densenet_Cifar10.py", line 111, in init
self.model = self.Dense_net(x)
File "Densenet_Cifar10.py", line 180, in Dense_net
x = self.transition_layer(x, scope='trans_1')
File "Densenet_Cifar10.py", line 140, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

do you solve the problem??

Answer 23 · 2019-04-27T08:01:36.000Z

@Demons-git @NatalieZou @taki0112
When I use this code, the program is reported as follows:
Traceback (most recent call last):
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 184, in
logits = DenseNet(x=batch_images, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 84, in init
self.model = self.Dense_net(x)
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 146, in Dense_net
x = self.transition_layer(x, scope='trans_'+str(i))
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 113, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'
I think this may be that in_channel is not an integer after _0.5. When I change it to x = conv_layer(x, filter=in_channel_1, kernel=[1,1], layer_name=scope+'_conv1'),
the network can run.
Then I use
Print(x)
Print(in_channel) to check their size。
I found that x and in_channel have two values.
Tensor("trans_0/Relu:0", shape=(?, 6, 6, 72), dtype=float32)
72
Tensor("trans_1/Relu:0", shape=(?, 3, 3, 120), dtype=float32)
120
From the above it seems that *0.5 should also be satisfied, and x and in_channel should also have only one value?
I want to know why this problem happened？

yes,I also have this problem, I run Dense_Cifar10.py, The program reports as follow：
Traceback (most recent call last):
File "Densenet_Cifar10.py", line 221, in
logits = DenseNet(x=input_x, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "Densenet_Cifar10.py", line 111, in init
self.model = self.Dense_net(x)
File "Densenet_Cifar10.py", line 180, in Dense_net
x = self.transition_layer(x, scope='trans_1')
File "Densenet_Cifar10.py", line 140, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

Hello，
I also encountered this problem, I changed this line of code so that I can run it.
in_channel = x.shape[-1]
Changed to
in_channel = x.get_shape().as_list()[-1]

Answer 24 · 2019-05-21T01:44:22.000Z

@NatalieZou @taki0112
When I use this code, the program is reported as follows:
Traceback (most recent call last):
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 184, in
logits = DenseNet(x=batch_images, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 84, in init
self.model = self.Dense_net(x)
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 146, in Dense_net
x = self.transition_layer(x, scope='trans_'+str(i))
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 113, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'
I think this may be that in_channel is not an integer after _0.5. When I change it to x = conv_layer(x, filter=in_channel_1, kernel=[1,1], layer_name=scope+'_conv1'),
the network can run.
Then I use
Print(x)
Print(in_channel) to check their size。
I found that x and in_channel have two values.
Tensor("trans_0/Relu:0", shape=(?, 6, 6, 72), dtype=float32)
72
Tensor("trans_1/Relu:0", shape=(?, 3, 3, 120), dtype=float32)
120
From the above it seems that *0.5 should also be satisfied, and x and in_channel should also have only one value?
I want to know why this problem happened？

yes,I also have this problem, I run Dense_Cifar10.py, The program reports as follow：
Traceback (most recent call last):
File "Densenet_Cifar10.py", line 221, in
logits = DenseNet(x=input_x, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "Densenet_Cifar10.py", line 111, in init
self.model = self.Dense_net(x)
File "Densenet_Cifar10.py", line 180, in Dense_net
x = self.transition_layer(x, scope='trans_1')
File "Densenet_Cifar10.py", line 140, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

do you solve the problem??

I also change code to run it at same place but not same change.
in_channel = x.shape[-1]
Changed to
in_channel = int(x.shape[-1])

Answer 25 · 2019-07-14T08:17:44.000Z

@yuffon It's all the same with the original code, the only part I change is "x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')"

Why can't I?
I use tensorflow1.10, cuda 9.0, 1080ti.
What optimizer do you use?

I used MomentumOptimizer, it's annotated in the code.

thank you very much.
How about the lr decay?
I have used adam as the optimizer, and the intial lr as 1e-4. This is a bad configuration.

I used MomentumOptimizer and the init_learning_rate is 1e-1

I see that your training acc can reach 90% in less than 10 epochs. The test acc also reaches 85% in 10 epochs. This is far beyond the results on my computer.

Could you give me your email, the .py file can't be send in github

my email is yuffonzhang@163.com
Thanks a lot.
The acc really sucks on my computer.

Hello, I also encountered a similar trouble that the valid accuracy is not high, I am using Adam optimization, can you send a training code to my mailbox? Wlshi111@aliyun.com Thank you!

Answer 26 · 2019-07-14T08:39:00.000Z

@NatalieZou @taki0112
When I use this code, the program is reported as follows:

Traceback (most recent call last):
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 184, in
logits = DenseNet(x=batch_images, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 84, in init
self.model = self.Dense_net(x)
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 146, in Dense_net
x = self.transition_layer(x, scope='trans_'+str(i))
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 113, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

I think this may be that in_channel is not an integer after _0.5. When I change it to x = conv_layer(x, filter=in_channel_1, kernel=[1,1], layer_name=scope+'_conv1'),
the network can run.

Then I use
Print(x)
Print(in_channel) to check their size。
I found that x and in_channel have two values.
Tensor("trans_0/Relu:0", shape=(?, 6, 6, 72), dtype=float32)
72
Tensor("trans_1/Relu:0", shape=(?, 3, 3, 120), dtype=float32)
120

From the above it seems that *0.5 should also be satisfied, and x and in_channel should also have only one value?
I want to know why this problem happened？

I also use * 0.5, but the code doesn't work. You can try filter = in_channel/2. The effect is the same, and print (x) and print (in_channel) are the same.

Answer 27 · 2019-07-14T08:39:52.000Z

@NatalieZou @taki0112
When I use this code, the program is reported as follows:

Traceback (most recent call last):
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 184, in
logits = DenseNet(x=batch_images, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 84, in init
self.model = self.Dense_net(x)
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 146, in Dense_net
x = self.transition_layer(x, scope='trans_'+str(i))
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 113, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

I think this may be that in_channel is not an integer after _0.5. When I change it to x = conv_layer(x, filter=in_channel_1, kernel=[1,1], layer_name=scope+'_conv1'),
the network can run.

Then I use
Print(x)
Print(in_channel) to check their size。
I found that x and in_channel have two values.
Tensor("trans_0/Relu:0", shape=(?, 6, 6, 72), dtype=float32)
72
Tensor("trans_1/Relu:0", shape=(?, 3, 3, 120), dtype=float32)
120

From the above it seems that *0.5 should also be satisfied, and x and in_channel should also have only one value?
I want to know why this problem happened？

I also use * 0.5, but the code doesn't work. You can try filter = in_channel/2. The effect is the same, and print (x) and print (in_channel) are the same.

Answer 28 · 2019-07-14T08:42:14.000Z

@NatalieZou @taki0112
When I use this code, the program is reported as follows:

Traceback (most recent call last):
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 184, in
logits = DenseNet(x=batch_images, nb_blocks=nb_block, filters=growth_k, training=training_flag).model
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 84, in init
self.model = self.Dense_net(x)
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 146, in Dense_net
x = self.transition_layer(x, scope='trans_'+str(i))
File "C:/Users/library/Desktop/densenet/net from git/Densenet-Tensorflow-master/MNIST/Densenet_MNIST.py", line 113, in transition_layer
x = conv_layer(x, filter=in_channel*0.5, kernel=[1,1], layer_name=scope+'_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float'

I think this may be that in_channel is not an integer after _0.5. When I change it to x = conv_layer(x, filter=in_channel_1, kernel=[1,1], layer_name=scope+'_conv1'),
the network can run.

Then I use
Print(x)
Print(in_channel) to check their size。
I found that x and in_channel have two values.
Tensor("trans_0/Relu:0", shape=(?, 6, 6, 72), dtype=float32)
72
Tensor("trans_1/Relu:0", shape=(?, 3, 3, 120), dtype=float32)
120

From the above it seems that *0.5 should also be satisfied, and x and in_channel should also have only one value?
I want to know why this problem happened？
maybe there are two transition_layer, nb_block = 2

Answer 29 · 2019-11-04T08:17:36.000Z

sir,I run this example, I found it may be error ,where the error code is " x = conv_layer(x, filter=in_channel * 0.5, kernel=[1, 1], layer_name=scope + '_conv1')
TypeError: unsupported operand type(s) for *: 'Dimension' and 'float' ",i can't solve it，so i want to find some ideas please.