Lmod Warning: ------------------------------------------------------------------------------- The following dependent module(s) are not currently loaded: curl/8.4.0 (required by: htslib/1.16) ------------------------------------------------------------------------------- The following have been reloaded with a version change: 1) curl/8.4.0 => curl/8.17.0 2) openssl/3.0.7 => openssl/3.6.0 2026-05-28 11:53:58.994557: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 11:54:15.024940: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set 2026-05-28 11:54:15.027503: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcuda.so.1 2026-05-28 11:54:15.506410: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties: pciBusID: 0000:db:00.0 name: NVIDIA H200 computeCapability: 9.0 coreClock: 1.98GHz coreCount: 132 deviceMemorySize: 139.72GiB deviceMemoryBandwidth: 4.47TiB/s 2026-05-28 11:54:15.506484: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 11:54:16.043521: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2026-05-28 11:54:16.043632: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 2026-05-28 11:54:16.462881: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10 2026-05-28 11:54:16.980538: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10 2026-05-28 11:54:17.528726: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10 2026-05-28 11:54:17.750690: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.11 2026-05-28 11:54:17.916616: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2026-05-28 11:54:17.921886: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0 2026-05-28 11:54:17.922286: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-05-28 11:54:17.922431: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set 2026-05-28 11:54:17.926075: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties: pciBusID: 0000:db:00.0 name: NVIDIA H200 computeCapability: 9.0 coreClock: 1.98GHz coreCount: 132 deviceMemorySize: 139.72GiB deviceMemoryBandwidth: 4.47TiB/s 2026-05-28 11:54:17.926117: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 11:54:17.926134: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2026-05-28 11:54:17.926144: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 2026-05-28 11:54:17.926152: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10 2026-05-28 11:54:17.926161: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10 2026-05-28 11:54:17.926169: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10 2026-05-28 11:54:17.926178: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.11 2026-05-28 11:54:17.926202: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2026-05-28 11:54:17.932461: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0 2026-05-28 11:54:17.932490: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 12:00:33.991983: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix: 2026-05-28 12:00:33.992079: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267] 0 2026-05-28 12:00:33.992091: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1280] 0: N 2026-05-28 12:00:33.996405: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1406] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 133852 MB memory) -> physical GPU (device: 0, name: NVIDIA H200, pci bus id: 0000:db:00.0, compute capability: 9.0) 2026-05-28 12:00:37.792796: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2) 2026-05-28 12:00:37.793283: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 2800000000 Hz 2026-05-28 12:00:40.838340: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2026-05-28 12:03:19.212527: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 2026-05-28 12:03:19.217605: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2026-05-28 12:16:04.213585: W tensorflow/stream_executor/gpu/asm_compiler.cc:63] Running ptxas --version returned 256 2026-05-28 12:16:04.431494: W tensorflow/stream_executor/gpu/redzone_allocator.cc:314] Internal: ptxas exited with non-zero error code 256, output: Relying on driver to perform ptx compilation. Modify $PATH to customize ptxas location. This message will be only logged once. 2026-05-28 12:16:34.339727: I tensorflow/stream_executor/cuda/cuda_blas.cc:1838] TensorFloat-32 will be used for the matrix multiplication. This will only be logged once. /home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py:595: UserWarning: Input dict contained keys ['coordinates', 'jitters', 'index', 'status', 'rev_comp'] which did not match any model input. They will be ignored by the model. [n for n in tensors.keys() if n not in ref_input_names]) /home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py:595: UserWarning: Input dict contained keys ['coordinates'] which did not match any model input. They will be ignored by the model. [n for n in tensors.keys() if n not in ref_input_names]) 2026-05-28 12:24:05.114329: W tensorflow/python/util/util.cc:348] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. 2026-05-28 12:24:09.325171: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 12:24:15.519111: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set 2026-05-28 12:24:15.520068: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcuda.so.1 2026-05-28 12:24:16.017946: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties: pciBusID: 0000:db:00.0 name: NVIDIA H200 computeCapability: 9.0 coreClock: 1.98GHz coreCount: 132 deviceMemorySize: 139.72GiB deviceMemoryBandwidth: 4.47TiB/s 2026-05-28 12:24:16.018025: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 12:24:16.022508: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2026-05-28 12:24:16.022603: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 2026-05-28 12:24:16.024635: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10 2026-05-28 12:24:16.025734: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10 2026-05-28 12:24:16.028887: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10 2026-05-28 12:24:16.030370: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.11 2026-05-28 12:24:16.031493: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2026-05-28 12:24:16.037618: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0 2026-05-28 12:24:16.037929: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-05-28 12:24:16.038023: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set 2026-05-28 12:24:16.040631: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties: pciBusID: 0000:db:00.0 name: NVIDIA H200 computeCapability: 9.0 coreClock: 1.98GHz coreCount: 132 deviceMemorySize: 139.72GiB deviceMemoryBandwidth: 4.47TiB/s 2026-05-28 12:24:16.040649: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 12:24:16.040661: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2026-05-28 12:24:16.040670: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 2026-05-28 12:24:16.040679: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10 2026-05-28 12:24:16.040688: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10 2026-05-28 12:24:16.040697: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10 2026-05-28 12:24:16.040706: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.11 2026-05-28 12:24:16.040715: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2026-05-28 12:24:16.047478: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0 2026-05-28 12:24:16.047499: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2026-05-28 12:30:14.277443: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix: 2026-05-28 12:30:14.277543: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267] 0 2026-05-28 12:30:14.277553: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1280] 0: N 2026-05-28 12:30:14.282577: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1406] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 133852 MB memory) -> physical GPU (device: 0, name: NVIDIA H200, pci bus id: 0000:db:00.0, compute capability: 9.0) /home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/keras/layers/core.py:1059: UserWarning: bpnet.model.arch is not loaded, but a Lambda layer uses it. It may cause errors. , UserWarning) batch: 0%| | 0/32 [00:00 physical GPU (device: 0, name: NVIDIA H200, pci bus id: 0000:db:00.0, compute capability: 9.0) 2026-05-28 12:52:23.159919: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:196] None of the MLIR optimization passes are enabled (registered 0 passes) 2026-05-28 12:52:23.174941: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 2800000000 Hz 2026-05-28 12:52:26.681812: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2026-05-28 12:55:20.596675: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 2026-05-28 12:55:20.602020: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2026-05-28 13:07:25.985719: W tensorflow/stream_executor/gpu/asm_compiler.cc:63] Running ptxas --version returned 256 2026-05-28 13:07:26.203469: W tensorflow/stream_executor/gpu/redzone_allocator.cc:314] Internal: ptxas exited with non-zero error code 256, output: Relying on driver to perform ptx compilation. Modify $PATH to customize ptxas location. This message will be only logged once. 2026-05-28 13:07:28.648392: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:28.648579: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:28.648759: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:31.290379: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:33.915162: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:36.552295: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:39.204208: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:42.724769: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:46.237946: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:49.759406: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device 2026-05-28 13:07:53.283106: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at cwise_op_gpu_base.cc:89 : Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device RuntimeError: module compiled against API version 0xe but this version of numpy is 0xd /home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/keras/layers/core.py:1059: UserWarning: bpnet.model.arch is not loaded, but a Lambda layer uses it. It may cause errors. , UserWarning) Traceback (most recent call last): File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1375, in _do_call return fn(*args) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1360, in _run_fn target_list, run_metadata) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1453, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InternalError: 2 root error(s) found. (0) Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device [[{{node gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/Abs}}]] [[gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Sub_grad/Reshape/_65]] (1) Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device [[{{node gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/Abs}}]] 0 successful operations. 0 derived errors ignored. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/users/shouvikm/miniconda3/envs/bpnet/bin/bpnet-shap", line 8, in sys.exit(shap_scores_main()) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/bpnet/cli/shap_scores.py", line 448, in shap_scores_main shap_scores(args, shap_scores_dir) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/bpnet/cli/shap_scores.py", line 326, in shap_scores counts_shap_inputs, progress_message=100) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py", line 294, in shap_values sample_phis = self.run(self.phi_symbolic(feature_ind), self.model_inputs, joint_input) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py", line 322, in run return self.session.run(out, feed_dict) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 968, in run run_metadata_ptr) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1191, in _run feed_dict_tensor, options, run_metadata) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1369, in _do_run run_metadata) File "/home/users/shouvikm/miniconda3/envs/bpnet/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1394, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InternalError: 2 root error(s) found. (0) Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device [[node gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/Abs (defined at /lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py:494) ]] [[gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Sub_grad/Reshape/_65]] (1) Internal: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device [[node gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/Abs (defined at /lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py:494) ]] 0 successful operations. 0 derived errors ignored. Errors may have originated from an input operation. Input Source operations connected to node gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/Abs: gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/sub (defined at /lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py:489) Input Source operations connected to node gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/Abs: gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/sub (defined at /lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py:489) Original stack trace for 'gradients/main_logsumexp_counts_bias_0/ReduceLogSumExp/Log_grad/Abs': File "/bin/bpnet-shap", line 8, in sys.exit(shap_scores_main()) File "/lib/python3.7/site-packages/bpnet/cli/shap_scores.py", line 448, in shap_scores_main shap_scores(args, shap_scores_dir) File "/lib/python3.7/site-packages/bpnet/cli/shap_scores.py", line 326, in shap_scores counts_shap_inputs, progress_message=100) File "/lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py", line 294, in shap_values sample_phis = self.run(self.phi_symbolic(feature_ind), self.model_inputs, joint_input) File "/lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py", line 229, in phi_symbolic self.phi_symbolics[i] = tf.gradients(out, self.model_inputs) File "/lib/python3.7/site-packages/tensorflow/python/ops/gradients_impl.py", line 318, in gradients_v2 unconnected_gradients) File "/lib/python3.7/site-packages/tensorflow/python/ops/gradients_util.py", line 684, in _GradientsHelper lambda: grad_fn(op, *out_grads)) File "/lib/python3.7/site-packages/tensorflow/python/ops/gradients_util.py", line 340, in _MaybeCompile return grad_fn() # Exit early File "/lib/python3.7/site-packages/tensorflow/python/ops/gradients_util.py", line 684, in lambda: grad_fn(op, *out_grads)) File "/lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py", line 327, in custom_grad return op_handlers[op.type](self, op, *grads) File "/lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py", line 477, in handler return nonlinearity_1d_handler(input_ind, explainer, op, *grads) File "/lib/python3.7/site-packages/shap/explainers/deep/deep_tf.py", line 494, in nonlinearity_1d_handler tf.tile(tf.abs(delta_in0), dup0) < 1e-6, File "/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py", line 201, in wrapper return target(*args, **kwargs) File "/lib/python3.7/site-packages/tensorflow/python/ops/math_ops.py", line 401, in abs return gen_math_ops._abs(x, name=name) File "/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py", line 56, in _abs "Abs", x=x, name=name) File "/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 750, in _apply_op_helper attrs=attr_protos, op_def=op_def) File "/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 3536, in _create_op_internal op_def=op_def) File "/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 1990, in __init__ self._traceback = tf_stack.extract_stack() ...which was originally created as op 'main_logsumexp_counts_bias_0/ReduceLogSumExp/Log', defined at: File "/bin/bpnet-shap", line 8, in sys.exit(shap_scores_main()) [elided 0 identical lines from previous traceback] File "/lib/python3.7/site-packages/bpnet/cli/shap_scores.py", line 448, in shap_scores_main shap_scores(args, shap_scores_dir) File "/lib/python3.7/site-packages/bpnet/cli/shap_scores.py", line 96, in shap_scores model = load_model(args.model, compile=False) File "/lib/python3.7/site-packages/tensorflow/python/keras/saving/save.py", line 212, in load_model return saved_model_load.load(filepath, compile, options) File "/lib/python3.7/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 138, in load keras_loader.load_layers(compile=compile) File "/lib/python3.7/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 376, in load_layers node_metadata.metadata) File "/lib/python3.7/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 417, in _load_layer obj, setter = self._revive_from_config(identifier, metadata, node_id) File "/lib/python3.7/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 435, in _revive_from_config self._revive_layer_from_config(metadata, node_id)) File "/lib/python3.7/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 495, in _revive_layer_from_config generic_utils.serialize_keras_class_and_config(class_name, config)) File "/lib/python3.7/site-packages/tensorflow/python/keras/layers/serialization.py", line 177, in deserialize printable_module_name='layer') File "/lib/python3.7/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 358, in deserialize_keras_object list(custom_objects.items()))) File "/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 2262, in from_config config, custom_objects=custom_objects) File "/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py", line 669, in from_config config, custom_objects) File "/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py", line 1285, in reconstruct_from_config process_node(layer, node_data) File "/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py", line 1233, in process_node output_tensors = layer(input_tensors, **kwargs) File "/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer_v1.py", line 786, in __call__ outputs = call_fn(cast_inputs, *args, **kwargs) File "/lib/python3.7/site-packages/tensorflow/python/keras/layers/core.py", line 917, in call result = self.function(inputs, **kwargs) File "/lib/python3.7/site-packages/bpnet/model/arch.py", line 446, in lambda x: tf.math.reduce_logsumexp(x, axis=-1, keepdims=True),