ValueError: Kernel shape must have the same length as input, but received kernel of shape (1, 3, 1, 100) and input of shape (None, None, 1, 16384, 1).

[Alice520rabbit]

When I am using DeepTE to identify TEs which have been identified by RepeatModeler, this error will happen, how can I do to solve this problem?

[songliVT]

This error seems to mean your input sequence is empty, can you double check what is the input matrix?

Song

Get Outlook for Androidhttps://aka.ms/AAb9ysg

---

From: Alice520rabbit @.> Sent: Friday, April 26, 2024 7:52:26 AM To: LiLabAtVT/DeepTE @.> Cc: Subscribed @.***> Subject: [LiLabAtVT/DeepTE] ValueError: Kernel shape must have the same length as input, but received kernel of shape (1, 3, 1, 100) and input of shape (None, None, 1, 16384, 1). (Issue #34)

When I am using DeepTE to identify TEs which have been identified by RepeatModeler, this error will happen, how can I do to solve this problem?

— Reply to this email directly, view it on GitHubhttps://github.com/LiLabAtVT/DeepTE/issues/34, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ACEEENV4K4LO5QVCW3KHOILY7I5XVAVCNFSM6AAAAABG2UMUSKVHI2DSMVQWIX3LMV43ASLTON2WKOZSGI3DKNRSGEYTAMQ. You are receiving this because you are subscribed to this thread.Message ID: @.***>

[Alice520rabbit]

Dear Song, I checked the input file to make sure that is a fasta file which is not empty, but the result is the same. Then I used the test_file to test, and the result is the same as the above. I am confused why this happened, could you give me some help? Best wishes!

[Alice520rabbit]

2024-04-26 20:46:04.459945: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0. 2024-04-26 20:46:04.460385: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used. 2024-04-26 20:46:04.466552: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used. 2024-04-26 20:46:04.541269: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-04-26 20:46:05.566745: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT start time is 1714135566.4546635 Step1: transfer fasta data to CNN input data Step2: classify TEs Step2: 2) domain information is not exist /public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/layers/convolutional/base_conv.py:99: UserWarning: Do not pass an input_shape/input_dim argument to a layer. When using Sequential models, prefer using an Input(shape) object as the first layer in the model instead. super().init( Traceback (most recent call last): File "/public/home/liqr/DeepTE-master/DeepTE.py", line 274, in main() File "/public/home/liqr/DeepTE-master/DeepTE.py", line 249, in main pipeline_no_m.classify_pipeline(model_dir, input_CNN_data_file, temp_store_opt_dir, sp_type,te_fam,prop_thr) File "/public/home/liqr/DeepTE-master/scripts/DeepTE_pipeline_no_modification.py", line 339, in classify_pipeline predict_te(model_file_dic[model_name], model_name, x_all_test_list, y_all_test_nm_list,input_spe_type,y_all_test_nm_list,prop_thr) File "/public/home/liqr/DeepTE-master/scripts/DeepTE_pipeline_no_modification.py", line 210, in predict_te model = load_model(model) ^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/saving/saving_api.py", line 183, in load_model return legacy_h5_format.load_model_from_hdf5(filepath) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/legacy/saving/legacy_h5_format.py", line 133, in load_model_from_hdf5 model = saving_utils.model_from_config( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/legacy/saving/saving_utils.py", line 85, in model_from_config return serialization.deserialize_keras_object( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/legacy/saving/serialization.py", line 495, in deserialize_keras_object deserialized_obj = cls.from_config( ^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 336, in from_config model.add(layer) File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 117, in add self._maybe_rebuild() File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 136, in _maybe_rebuild self.build(input_shape) File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/layers/layer.py", line 224, in build_wrapper original_build_method(*args, **kwargs) File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 177, in build x = layer(x) ^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/utils/traceback_utils.py", line 123, in error_handler raise e.with_traceback(filtered_tb) from None File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/ops/operation_utils.py", line 185, in compute_conv_output_shape raise ValueError( ValueError: Kernel shape must have the same length as input, but received kernel of shape (1, 3, 1, 100) and input of shape (None, None, 1, 16384, 1).

[songliVT]

Hello Alice,

I would like to suggest you contact Dr. Ou and use their package, EDTA, for your annotation of TE work.

https://github.com/oushujun/EDTA

DeepTE was a pet project from a previous student who has now moved on to a different position. We no longer have funding to maintain this package. Using EDTA would be a better and more sustainable solution for your task.

Best, Song

---

Associate Professor in Plant Genomics and Bioinformatics School of Plant and Environmental Sciences Virginia Polytechnic Institute and State University

zoom https://virginiatech.zoom.us/j/8790572835

---

From: Alice520rabbit @.> Sent: Friday, April 26, 2024 9:16 AM To: LiLabAtVT/DeepTE @.> Cc: Li, Song @.>; Comment @.> Subject: Re: [LiLabAtVT/DeepTE] ValueError: Kernel shape must have the same length as input, but received kernel of shape (1, 3, 1, 100) and input of shape (None, None, 1, 16384, 1). (Issue #34)

2024-04-26 20:46:04.459945: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0. 2024-04-26 20:46:04.460385: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used. 2024-04-26 20:46:04.466552: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used. 2024-04-26 20:46:04.541269: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-04-26 20:46:05.566745: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT start time is 1714135566.4546635 Step1: transfer fasta data to CNN input data Step2: classify TEs Step2: 2) domain information is not exist /public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/layers/convolutional/base_conv.py:99: UserWarning: Do not pass an input_shape/input_dim argument to a layer. When using Sequential models, prefer using an Input(shape) object as the first layer in the model instead. super().init( Traceback (most recent call last): File "/public/home/liqr/DeepTE-master/DeepTE.py", line 274, in main() File "/public/home/liqr/DeepTE-master/DeepTE.py", line 249, in main pipeline_no_m.classify_pipeline(model_dir, input_CNN_data_file, temp_store_opt_dir, sp_type,te_fam,prop_thr) File "/public/home/liqr/DeepTE-master/scripts/DeepTE_pipeline_no_modification.py", line 339, in classify_pipeline predict_te(model_file_dic[model_name], model_name, x_all_test_list, y_all_test_nm_list,input_spe_type,y_all_test_nm_list,prop_thr) File "/public/home/liqr/DeepTE-master/scripts/DeepTE_pipeline_no_modification.py", line 210, in predict_te model = load_model(model) ^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/saving/saving_api.py", line 183, in load_model return legacy_h5_format.load_model_from_hdf5(filepath) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/legacy/saving/legacy_h5_format.py", line 133, in load_model_from_hdf5 model = saving_utils.model_from_config( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/legacy/saving/saving_utils.py", line 85, in model_from_config return serialization.deserialize_keras_object( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/legacy/saving/serialization.py", line 495, in deserialize_keras_object deserialized_obj = cls.from_config( ^^^^^^^^^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 336, in from_config model.add(layer) File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 117, in add self._maybe_rebuild() File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 136, in _maybe_rebuild self.build(input_shape) File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/layers/layer.py", line 224, in build_wrapper original_build_method(*args, **kwargs) File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/models/sequential.py", line 177, in build x = layer(x) ^^^^^^^^ File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/utils/traceback_utils.py", line 123, in error_handler raise e.with_traceback(filtered_tb) from None File "/public/home/liqr/miniconda3/envs/repbox-re/lib/python3.12/site-packages/keras/src/ops/operation_utils.py", line 185, in compute_conv_output_shape raise ValueError( ValueError: Kernel shape must have the same length as input, but received kernel of shape (1, 3, 1, 100) and input of shape (None, None, 1, 16384, 1).

— Reply to this email directly, view it on GitHubhttps://github.com/LiLabAtVT/DeepTE/issues/34#issuecomment-2079377467, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ACEEENROJBXRQ2PQP6Q2I6DY7JHRFAVCNFSM6AAAAABG2UMUSKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANZZGM3TONBWG4. You are receiving this because you commented.Message ID: @.***>