The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 2000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
missing keys: 58;
unexpected keys: 116;
The config attributes {'addition_embed_type': None, 'addition_embed_type_num_heads': 64, 'addition_time_embed_dim': None, 'attention_type': 'default', 'class_embeddings_concat': False, 'conv_in_kernel': 3, 'conv_out_kernel': 3, 'cross_attention_norm': None, 'decay': 0.9999, 'dropout': 0.0, 'encoder_hid_dim': None, 'encoder_hid_dim_type': None, 'inv_gamma': 1.0, 'mid_block_only_cross_attention': None, 'min_decay': 0.0, 'num_attention_heads': None, 'optimization_step': 2000, 'power': 0.6666666666666666, 'projection_class_embeddings_input_dim': None, 'resnet_out_scale_factor': 1.0, 'resnet_skip_time_act': False, 'reverse_transformer_layers_per_block': None, 'time_cond_proj_dim': None, 'time_embedding_act_fn': None, 'time_embedding_dim': None, 'time_embedding_type': 'positional', 'timestep_post_act': None, 'transformer_layers_per_block': 1, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet3DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
missing keys: 162;
unexpected keys: 154;
Couldn't connect to the Hub: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/prs-eth/marigold-normals-v0-1 (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f653bf323e0>: Failed to establish a new connection: [Errno 101] Network is unreachable'))"), '(Request ID: d7c9f5ef-655c-49bd-96ba-e44171d05d77)').
Will try to load from local cache.
Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 5.02it/s]
Potentially unsupported prediction_type='None'; values supported by the pipeline: ('normals',).
Marigold predictions...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00, 1.87s/it]
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1727491211.127214 3424952 gl_context_egl.cc:85] Successfully initialized EGL. Major : 1 Minor: 5
I0000 00:00:1727491211.199523 3432240 gl_context.cc:357] GL version: 3.2 (OpenGL ES 3.2 NVIDIA 535.183.01), renderer: NVIDIA GeForce RTX 4090/PCIe/SSE2
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
W0000 00:00:1727491211.358616 3432178 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
ERROR: No subgraph in the model.
E0000 00:00:1727491211.383328 3424952 calculator_graph.cc:896] INTERNAL: CalculatorGraph::Run() failed:
Calculator::Open() for node "poselandmarkcpuposelandmarkbyroicpuinferencecalculatorposelandmarkcpuposelandmarkbyroicpu__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:442) (interpreter_builder(&interpreter))==(kTfLiteOk)
Traceback (most recent call last):
File "/home/sherry/lzd/MagicMan/./thirdparties/econ/lib/common/imutils.py", line 99, in get_keypoints
results = holistic.process(image)
File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solutions/holistic.py", line 160, in process
results = super().process(input_data={'image': image})
File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solution_base.py", line 340, in process
self._graph.wait_until_idle()
RuntimeError: CalculatorGraph::Run() failed:
Calculator::Open() for node "poselandmarkcpuposelandmarkbyroicpuinferencecalculatorposelandmarkcpuposelandmarkbyroicpu__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:442) (interpreter_builder(&interpreter))==(kTfLiteOk)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/sherry/lzd/MagicMan/inference.py", line 513, in
main()
File "/home/sherry/lzd/MagicMan/inference.py", line 275, in main
smpl_dict = smpl_estimator.estimate_smpl(ref_rgb_pil)
File "/home/sherry/lzd/MagicMan/thirdparties/econ/lib/common/smpl_utils.py", line 105, in estimate_smpl
arr_dict = process_image(img_pil)
File "/home/sherry/lzd/MagicMan/./thirdparties/econ/lib/common/imutils.py", line 212, in process_image
landmarks = get_keypoints(img_np)
File "/home/sherry/lzd/MagicMan/./thirdparties/econ/lib/common/imutils.py", line 95, in get_keypoints
with mp_holistic.Holistic(
File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solution_base.py", line 604, in exit
self.close()
File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solution_base.py", line 362, in close
self._graph.close()
RuntimeError: CalculatorGraph::Run() failed:
Calculator::Open() for node "poselandmarkcpuposelandmarkbyroicpuinferencecalculatorposelandmarkcpuposelandmarkbyroicpu__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:442) (interpreter_builder(&interpreter))==(kTfLiteOk)
The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 2000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
missing keys: 58;
unexpected keys: 116;
The config attributes {'addition_embed_type': None, 'addition_embed_type_num_heads': 64, 'addition_time_embed_dim': None, 'attention_type': 'default', 'class_embeddings_concat': False, 'conv_in_kernel': 3, 'conv_out_kernel': 3, 'cross_attention_norm': None, 'decay': 0.9999, 'dropout': 0.0, 'encoder_hid_dim': None, 'encoder_hid_dim_type': None, 'inv_gamma': 1.0, 'mid_block_only_cross_attention': None, 'min_decay': 0.0, 'num_attention_heads': None, 'optimization_step': 2000, 'power': 0.6666666666666666, 'projection_class_embeddings_input_dim': None, 'resnet_out_scale_factor': 1.0, 'resnet_skip_time_act': False, 'reverse_transformer_layers_per_block': None, 'time_cond_proj_dim': None, 'time_embedding_act_fn': None, 'time_embedding_dim': None, 'time_embedding_type': 'positional', 'timestep_post_act': None, 'transformer_layers_per_block': 1, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet3DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
missing keys: 162;
unexpected keys: 154;
Couldn't connect to the Hub: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/prs-eth/marigold-normals-v0-1 (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f653bf323e0>: Failed to establish a new connection: [Errno 101] Network is unreachable'))"), '(Request ID: d7c9f5ef-655c-49bd-96ba-e44171d05d77)'). Will try to load from local cache. Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 5.02it/s] Potentially unsupported
prediction_type='None'; values supported by the pipeline: ('normals',). Marigold predictions...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00, 1.87s/it] WARNING: All log messages before absl::InitializeLog() is called are written to STDERRI0000 00:00:1727491211.127214 3424952 gl_context_egl.cc:85] Successfully initialized EGL. Major : 1 Minor: 5 I0000 00:00:1727491211.199523 3432240 gl_context.cc:357] GL version: 3.2 (OpenGL ES 3.2 NVIDIA 535.183.01), renderer: NVIDIA GeForce RTX 4090/PCIe/SSE2 INFO: Created TensorFlow Lite XNNPACK delegate for CPU. W0000 00:00:1727491211.358616 3432178 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors. ERROR: No subgraph in the model.
E0000 00:00:1727491211.383328 3424952 calculator_graph.cc:896] INTERNAL: CalculatorGraph::Run() failed: Calculator::Open() for node "poselandmarkcpuposelandmarkbyroicpuinferencecalculatorposelandmarkcpuposelandmarkbyroicpu__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:442) (interpreter_builder(&interpreter))==(kTfLiteOk) Traceback (most recent call last): File "/home/sherry/lzd/MagicMan/./thirdparties/econ/lib/common/imutils.py", line 99, in get_keypoints results = holistic.process(image) File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solutions/holistic.py", line 160, in process results = super().process(input_data={'image': image}) File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solution_base.py", line 340, in process self._graph.wait_until_idle() RuntimeError: CalculatorGraph::Run() failed: Calculator::Open() for node "poselandmarkcpuposelandmarkbyroicpuinferencecalculatorposelandmarkcpuposelandmarkbyroicpu__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:442) (interpreter_builder(&interpreter))==(kTfLiteOk)
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "/home/sherry/lzd/MagicMan/inference.py", line 513, in
main()
File "/home/sherry/lzd/MagicMan/inference.py", line 275, in main
smpl_dict = smpl_estimator.estimate_smpl(ref_rgb_pil)
File "/home/sherry/lzd/MagicMan/thirdparties/econ/lib/common/smpl_utils.py", line 105, in estimate_smpl
arr_dict = process_image(img_pil)
File "/home/sherry/lzd/MagicMan/./thirdparties/econ/lib/common/imutils.py", line 212, in process_image
landmarks = get_keypoints(img_np)
File "/home/sherry/lzd/MagicMan/./thirdparties/econ/lib/common/imutils.py", line 95, in get_keypoints
with mp_holistic.Holistic(
File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solution_base.py", line 604, in exit
self.close()
File "/home/sherry/anaconda3/envs/magicman/lib/python3.10/site-packages/mediapipe/python/solution_base.py", line 362, in close
self._graph.close()
RuntimeError: CalculatorGraph::Run() failed:
Calculator::Open() for node "poselandmarkcpuposelandmarkbyroicpuinferencecalculatorposelandmarkcpuposelandmarkbyroicpu__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:442) (interpreter_builder(&interpreter))==(kTfLiteOk)