$ sudo python example.py
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcurand.so locally
I tensorflow/core/common_runtime/gpu/gpu_init.cc:102] Found device 0 with properties:
name: Tesla K20c
major: 3 minor: 5 memoryClockRate (GHz) 0.7055
pciBusID 0000:03:00.0
Total memory: 4.69GiB
Free memory: 4.61GiB
I tensorflow/core/common_runtime/gpu/gpu_init.cc:102] Found device 1 with properties:
name: NVS 315
major: 2 minor: 1 memoryClockRate (GHz) 1.046
pciBusID 0000:04:00.0
Total memory: 1020.69MiB
Free memory: 627.60MiB
I tensorflow/core/common_runtime/gpu/gpu_init.cc:59] cannot enable peer access from device ordinal 0 to device ordinal 1
I tensorflow/core/common_runtime/gpu/gpu_init.cc:59] cannot enable peer access from device ordinal 1 to device ordinal 0
I tensorflow/core/common_runtime/gpu/gpu_init.cc:126] DMA: 0 1
I tensorflow/core/common_runtime/gpu/gpu_init.cc:136] 0: Y N
I tensorflow/core/common_runtime/gpu/gpu_init.cc:136] 1: N Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:717] Creating TensorFlow device (/gpu:0) -> (device: 0, name: Tesla K20c, pci bus id: 0000:03:00.0)
I tensorflow/core/common_runtime/gpu/gpu_device.cc:684] Ignoring gpu device (device: 1, name: NVS 315, pci bus id: 0000:04:00.0) with Cuda compute capability 2.1. The minimum required Cuda capability is 3.5.
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 1.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 2.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 4.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 8.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 16.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 32.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 64.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 128.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 256.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 512.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 1.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 2.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 4.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 8.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 16.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 32.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 64.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 128.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 256.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 512.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 1.00GiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 2.00GiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 4.00GiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 8.00GiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:73] Allocating 4.32GiB bytes.
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:83] GPU 0 memory begins at 0x704460000 extends to 0x8187c2000

HELP.
Thanks~!

Thank you for your excellent implementation of spatial transformer in Tensorflow !
However, I notice the 53-th line of "example.py" as follows:

• "h_fc1 = tf.matmul(tf.zeros([num_batch, 1200 * 1600 * 3]), W_fc1) + b_fc1".
  What confuses me is the absence of some activation function, such as tf.nn.tanh or tf.nn.sigmoid.
  Without tanh or sigmoid, the range of theta is certainly not limited. What if a proper activation function is used here ? Could you please provide a good recommendation ?
  Thank you !

Yes. The output of the localization network is theta.

But it seems that there is no code for localization network in your code.

THX for your great effort.
I try to run the code but found that acc remains 0.119 for a long time and loss remains about 2.3000. How to optimize it?

Hi david,

I ran the cluttered_mnist example based on your implementation of SPN. I used exactly the same data as you, and the same code. However, I got 'nan' loss somewhere during training. Do you have any idea about this.

Thanks,

Hi, thanks for releasing this implementation! Unfortunately I can't seem to get the results I expect when using just an identity transformation? Correct me if I am doing something wrong, but using the following piece of code I would expect x_in = x_out?

`
b, h, w, c = [1, 5, 5, 1]
x_in = tf.random.uniform(shape=(b, h, w, c))

identity = np.array([[1., 0., 0.], [0., 1., 0.]])
identity = identity.flatten()
theta = tf.Variable(initial_value=identity)

x_out = transformer(x_in, theta, out_size=(h, w))

print(x_in)
print(x_out)
print(theta)
`

训练完后得到什么呢，请问STN怎么用于矫正扭曲文字图片