Closed lyclyc171 closed 2 years ago
lyclyc171
commented
2 years ago It seems that my input is incorrect, but if I understand correctly, just put the tfrecords file in root dir and I don't have to add "-d ${your-data-path}". right? P.S. sorry I can't upload my screenshot now
xmeng525
commented
2 years ago Hi, you do need to add "-d ${your-data-path}". Please let me know if you have any followup questions.
lyclyc171
commented
2 years ago lyl
hi, I don't have the dataset "1-spp dataset(19 GB)" but only the "bw_data_128x128_1scenes_60ips_50ppi_test.tfrecords" , which you call it "packed testdata for scene 'classroom'", in the MCDNBG_ROOT dir, so what is ${your-data-path} in this situation?
I tried "python network_test.py -d "classroom" " or "python network_test.py -d bw_data_128x128_1scenes_60ips_50ppi_test.tfrecords" but neither of them work
xmeng525
commented
2 years ago Try python network_test.py -r .
xmeng525
commented
2 years ago your-data-path is the the path to your data. If you tfrecord is in the root dir, your-data-path = .
lyclyc171
commented
2 years ago nope, I tried "python network_test.py -d ./" "python network_test.py -d ." "python network_test.py -r ./" "python network_test.py -r ." just not working, show the same output as I mention. could you find any clue in the output log I put in the first comment?
xmeng525
commented
2 years ago Hi I don't have the repo on my PC and I'm afraid I cannot help with it now. I guess the kernels are not compiled successfully. What is your CUDA version?
lyclyc171
commented
2 years ago I have cuda 10.2 in my system but I install cuda 10.0.13 in conda environment, and I change the g++ lib searching path to
"g++ -std=c++11 -shared -o bilateral_kernels.so bilateral_kernels.cc \ -L ~/anaconda3/envs/BilDenoiser/lib \ bilateral_kernels.cu.o ${TF_CFLAGS[@]} -fPIC -lcudart ${TF_LFLAGS[@]} "
so it should be cuda 10.0.13, and here is compiling log:
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) -I/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include -L/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow In file included from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/ConfigureVectorization.h:384:0, from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/Core:22, from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/unsupported/Eigen/CXX11/Tensor:14, from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/third_party/eigen3/unsupported/Eigen/CXX11/Tensor:1, from bilateral_kernels.cu.cc:7: /usr/local/cuda-10.2/bin/../targets/x86_64-linux/include/host_defines.h:54:2: warning: #warning "host_defines.h is an internal header file and must not be used directly. This file will be removed in a future CUDA release. Please use cuda_runtime_api.h or cuda_runtime.h instead." [-Wcpp]
^~~
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/absl/strings/string_view.h(496): warning: expression has no effect
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/google/protobuf/arena_impl.h(55): warning: integer conversion resulted in a change of sign
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/google/protobuf/arena_impl.h(309): warning: integer conversion resulted in a change of sign
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/google/protobuf/arena_impl.h(310): warning: integer conversion resulted in a change of sign
bilateral_kernels.cu.cc(579): warning: variable "back" was declared but never referenced
In file included from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/ConfigureVectorization.h:384:0, from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/Core:22, from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/unsupported/Eigen/CXX11/Tensor:14, from /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/third_party/eigen3/unsupported/Eigen/CXX11/Tensor:1, from bilateral_kernels.cu.cc:7: /usr/local/cuda-10.2/bin/../targets/x86_64-linux/include/host_defines.h:54:2: warning: #warning "host_defines.h is an internal header file and must not be used directly. This file will be removed in a future CUDA release. Please use cuda_runtime_api.h or cuda_runtime.h instead." [-Wcpp]
^~~
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/absl/strings/string_view.h(496): warning: expression has no effect
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/google/protobuf/arena_impl.h(55): warning: integer conversion resulted in a change of sign
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/google/protobuf/arena_impl.h(309): warning: integer conversion resulted in a change of sign
/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/include/google/protobuf/arena_impl.h(310): warning: integer conversion resulted in a change of sign
looks the "bilateral_kernels.so" successfully compiled in the "./bilateral_kernels", but I am not sure about its correctness.
lyclyc171
commented
2 years ago BTW, I install tensorflow-gpu 1.13.1 instead of tensorflow 1.13.1, would this cause any problems?
xmeng525
commented
2 years ago I checked the log and I noticed that tensorflow is using cuda 10.2 in your system, not cuda 10.0. Maybe the tensorflow-GPU is still using the cuda in you system, not the one in conda invironment. Would you please try to install cuda 10.0 in your system, and try to install tensorflow-gpu with cuda10.0 using pip? BTW, tensorflow-gpu is the correct version. Not tensorflow. I’ll make it clear in readme, thank you for your reminder!
On Tue, Aug 16, 2022 at 12:38 AM lyclyc171 @.***> wrote:
BTW, I install tensorflow-gpu 1.13.1 instead of tensorflow 1.13.1, would this cause any problems?
— Reply to this email directly, view it on GitHub https://github.com/xmeng525/RealTimeDenoisingNeuralBilateralGrid/issues/9#issuecomment-1216261625, or unsubscribe https://github.com/notifications/unsubscribe-auth/AGC2OPIP6IR7YT4QCCIZWJ3VZNAPPANCNFSM56ULCISA . You are receiving this because you commented.Message ID: @.*** com>
-- Xiaoxu Meng
lyclyc171
commented
2 years ago Hi, thanks for your reply, I have solved this problem, the key is I install tensorflow-base and tensorflow-gpu both, and tensorflow-base has higher priority to be triggered. So I uninstall all the tensorflows and reinstall tensorflow-gpu then everything is fine.
But there's still a little problem, I download the 1-spp BMFR dataset and put it in ${MCDNBG_ROOT}/data/BMFR_dataset/classroom. Next, I download temporal accumulated dataset and unzip it to the same path. however, when I run "python network_test.py -d ${MCDNBG_ROOT}/data/BMFR_dataset/classroom", the project cannot find the data with "Exception: File '../../dataset/dataset_blockwise/BMFR-dataset/./data/BMFR_dataset/classroom/inputs/albedo0.exr' is not an EXR file. "
then I check network_test.py and maybe it should be "python network_test -r ${your-data-path}" ?
xmeng525
commented
2 years ago Glad to hear that the problem is solved! If you are using the original images for testing, the data loader will encode the data to tfrecords and use the tfrecord for testing. When the images are encoded, it will print the index of the image (check dataLoader.py line 68). If there is no index printed, you may want to check the dataLoader for detail.
On Tue, Aug 16, 2022 at 7:05 PM lyclyc171 @.***> wrote:
Hi, thanks for your reply, I have solved this problem, the key is I install tensorflow-base and tensorflow-gpu both, and tensorflow-base has higher priority to be triggered. So I uninstall all the tensorflows and reinstall tensorflow-gpu then everything is fine.
But there's still a little problem, I download the 1-spp BMFR dataset and put it in ${MCDNBG_ROOT}/data/BMFR_dataset/classroom. Next, I download temporal accumulated dataset and unzip it to the same path. however, when I run "python network_test.py -d ${MCDNBG_ROOT}/data/BMFR_dataset/classroom", the project cannot find the data with "Exception: File '../../dataset/dataset_blockwise/BMFR-dataset/./data/BMFR_dataset/classroom/inputs/albedo0.exr' is not an EXR file. "
then I check network_test.py and maybe it should be "python network_test -r ${your-data-path}" ? When I use -r, the testing could running but end up with " ======================End of Report========================== WARNING:tensorflow:From /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/training/saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version. Instructions for updating: Use standard file APIs to check for files with this prefix. Start Testing... Finish testing 0 images. " I don't know why it find data but test 0 images
— Reply to this email directly, view it on GitHub https://github.com/xmeng525/RealTimeDenoisingNeuralBilateralGrid/issues/9#issuecomment-1217373770, or unsubscribe https://github.com/notifications/unsubscribe-auth/AGC2OPOKG5HZ2NVDHSM6X6DVZRCHZANCNFSM56ULCISA . You are receiving this because you commented.Message ID: @.*** com>
-- Xiaoxu Meng
lyclyc171
commented
2 years ago thanks for explaining, I do see the encoding process, but I do it by typing "python network_test -r ${your-data-path}", not "python network_test -d ${your-data-path} " as you write in readme.md. So I wonder it is a typo or not ?
xmeng525
commented
2 years ago Yes. It is a typo
On Wed, Aug 17, 2022 at 2:29 AM lyclyc171 @.***> wrote:
thanks for explaining, I do see the encoding process, but I do it by typing "python network_test -r ${your-data-path}", not "python network_test -d ${your-data-path} " as you write in readme.md. So I wonder it is a typo or not ?
— Reply to this email directly, view it on GitHub https://github.com/xmeng525/RealTimeDenoisingNeuralBilateralGrid/issues/9#issuecomment-1217753760, or unsubscribe https://github.com/notifications/unsubscribe-auth/AGC2OPOWU7AH7GRQCA54M3LVZSWHVANCNFSM56ULCISA . You are receiving this because you commented.Message ID: @.*** com>
-- Xiaoxu Meng
Hi there, I wanna repro your nice work. I am using "packed testdata for scene 'classroom'" instead of "1-spp dataser" for some reason. So I put the pre-train models in "${MCDNGB_ROOT}/classroom/model" and put the tfrecords in ${MCDNBG_ROOT}, but when I run network_test.py an error in 'create_bi_grid' is encountered, here is output log:
`>/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) bw_data_128x128_1scenes_60ips_50ppi_test.tfrecords exisits. WARNING:tensorflow:From /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py:1419: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Colocations handled automatically by placer. Creating GuideNet ... DEBUG:: InShape = [None, None, None, 10] DEBUG:: OutShape = [None, None, None, 20] prep layer input_shape: [None, None, None, 10] prep layer output_shape: [None, None, None, 20] DEBUG:: InShape = [None, None, None, 20] DEBUG:: OutShape = [None, None, None, 5] Final layer out_shape: [None, None, None, 5] WARNING:tensorflow:From /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/ops/losses/losses_impl.py:277: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. 2022-08-16 12:11:42.914711: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2022-08-16 12:11:42.937703: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3000000000 Hz 2022-08-16 12:11:42.937994: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x55c4ffe76090 executing computations on platform Host. Devices: 2022-08-16 12:11:42.938011: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0):,
WARNING:tensorflow:From /home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/profiler/internal/flops_registry.py:142: tensor_shape_from_node_def_name (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.compat.v1.graph_util.remove_training_nodes
Parsing Inputs...
Incomplete shape.
Incomplete shape.
Incomplete shape.
Incomplete shape.
Incomplete shape.
Incomplete shape.
=========================Options============================= -max_depth 10000 -min_bytes 0 -min_peak_bytes 0 -min_residual_bytes 0 -min_output_bytes 0 -min_micros 0 -min_accelerator_micros 0 -min_cpu_micros 0 -min_params 0 -min_float_ops 1 -min_occurrence 0 -step -1 -order_by float_ops -account_type_regexes . -start_name_regexes . -trim_name_regexes
-show_name_regexes .* -hide_name_regexes
-account_displayed_op_only true -select float_ops -output stdout:
==================Model Analysis Report====================== Incomplete shape. Incomplete shape. Incomplete shape. Incomplete shape. Incomplete shape. Incomplete shape.
Doc: op: The nodes are operation kernel type, such as MatMul, Conv2D. Graph nodes belonging to the same type are aggregated together. flops: Number of float operations. Note: Please read the implementation for the math behind it.
Profile: node name | # float_ops Add 7.53k float_ops (100.00%, 49.93%) Mul 7.53k float_ops (50.07%, 49.93%) Equal 14 float_ops (0.13%, 0.09%) Sub 4 float_ops (0.04%, 0.03%) Mean 2 float_ops (0.01%, 0.01%)
======================End of Report========================== Parsing Inputs... Incomplete shape. Incomplete shape. Incomplete shape. Incomplete shape. Incomplete shape. Incomplete shape.
=========================Options============================= -max_depth 10000 -min_bytes 0 -min_peak_bytes 0 -min_residual_bytes 0 -min_output_bytes 0 -min_micros 0 -min_accelerator_micros 0 -min_cpu_micros 0 -min_params 0 -min_float_ops 0 -min_occurrence 0 -step -1 -order_by name -account_type_regexes _trainable_variables -start_name_regexes . -trim_name_regexes
-show_name_regexes . -hide_name_regexes
-account_displayed_op_only true -select params -output stdout:
==================Model Analysis Report======================
Doc: op: The nodes are operation kernel type, such as MatMul, Conv2D. Graph nodes belonging to the same type are aggregated together. param: Number of parameters (in the Variable).
Profile: node name | # parameters VariableV2 7.53k params (100.00%, 100.00%)
======================End of Report========================== Traceback (most recent call last): File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call return fn(*args) File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1317, in _run_fn self._extend_graph() File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1352, in _extend_graph tf_session.ExtendSession(self._session) tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'CreateBiGrid' used by {{node BilateralGrid/CreateBiGrid}}with these attrs: [] Registered devices: [CPU, XLA_CPU] Registered kernels: device='GPU'
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "network_test.py", line 117, in
sess.run(tf.global_variables_initializer())
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run
run_metadata)
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'CreateBiGrid' used by node BilateralGrid/CreateBiGrid (defined at :74) with these attrs: []
Registered devices: [CPU, XLA_CPU]
Registered kernels:
device='GPU'
Caused by op 'BilateralGrid/CreateBiGrid', defined at: File "network_test.py", line 101, in
guide_net = model.inference()
File "/home/i/Documents/BilateralGridDenoiser/network.py", line 41, in inference
grid_1 = self._create_grid(self.source[:,:,:,0:3], guide_1, self.ss, self.sr)
File "/home/i/Documents/BilateralGridDenoiser/network.py", line 141, in _create_grid
output = create_bi_grid(input_image, input_guide, input_attrs)
File "", line 74, in create_bi_grid
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
op_def=op_def)
File "/home/i/anaconda3/envs/BilDenoiser/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1801, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'CreateBiGrid' used by node BilateralGrid/CreateBiGrid (defined at:74) with these attrs: []
Registered devices: [CPU, XLA_CPU]
Registered kernels:
device='GPU'
Could you help me to figure out what's wrong with this process? Thank you