Cộng đồng Hỏi & Đáp của Inflearn

강의코드를 그대로 구현할시

여기서 일단 설치가 완벽하게 안됩니다. 아래에러코드, 무시하고 진행해도 되는거 같지만 일단 완벽하게 진행하려고 저같은 경우는

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. yellowbrick 1.3.post1 requires numpy<1.20,>=1.16.0, but you have numpy 1.21.5 which is incompatible. multiprocess 0.70.12.2 requires dill>=0.3.4, but you have dill 0.3.1.1 which is incompatible. gym 0.17.3 requires cloudpickle<1.7.0,>=1.2.0, but you have cloudpickle 2.0.0 which is incompatible. google-colab 1.0.0 requires requests~=2.23.0, but you have requests 2.27.1 which is incompatible. datascience 0.10.6 requires folium==0.2.1, but you have folium 0.8.3 which is incompatible. albumentations 0.1.12 requires imgaug<0.2.7,>=0.2.5, but you have imgaug 0.2.9 which is incompatible.

위의 코드를 실행하고 진행하였구요

이상태로 진행하면 

test 코드에서 아래 에러가 발생하고

ModuleNotFoundError: No module named 'tensorflow.python.keras.applications'

tensorflow 2.7버전으로 바꾸고 실행하면 진행됩니다

그후에 모델링 학습을 하게되면

tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found. (0) UNKNOWN: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/conv2d/Conv2D (defined at /usr/local/lib/python3.7/dist-packages/keras/layers/convolutional.py:238) ]] [[Identity_321/_240]] (1) UNKNOWN: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/conv2d/Conv2D (defined at /usr/local/lib/python3.7/dist-packages/keras/layers/convolutional.py:238) ]] 0 successful operations. 0 derived errors ignored. [Op:__inference__dist_train_step_86045] Errors may have originated from an input operation. Input Source operations connected to node center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/conv2d/Conv2D: In[0] center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/zero_padding2d/Pad (defined at /usr/local/lib/python3.7/dist-packages/keras/backend.py:3672) In[1] center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/conv2d/Conv2D/ReadVariableOp: Operation defined at: (most recent call last) >>> File "/usr/lib/python3.7/threading.py", line 890, in _bootstrap >>> self._bootstrap_inner() >>> >>> File "/usr/lib/python3.7/threading.py", line 926, in _bootstrap_inner >>> self.run() >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/model_lib_v2.py", line 593, in train_step_fn >>> loss = eager_train_step( >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/model_lib_v2.py", line 253, in eager_train_step >>> losses_dict, _ = _compute_losses_and_predictions_dicts( >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/model_lib_v2.py", line 118, in _compute_losses_and_predictions_dicts >>> prediction_dict = model.predict( >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/meta_architectures/center_net_meta_arch.py", line 2847, in predict >>> features_list = self._feature_extractor(preprocessed_inputs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/center_net_hourglass_feature_extractor.py", line 53, in call >>> return self._network(inputs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 431, in call >>> if self.initial_downsample: >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 432, in call >>> inputs = self.downsample_input(inputs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 174, in call >>> return self.residual_block(self.conv_block(inputs)) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 94, in call >>> net = self.conv(net) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/layers/convolutional.py", line 246, in call >>> outputs = self.convolution_op(inputs, self.kernel) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/layers/convolutional.py", line 238, in convolution_op >>> name=self.__class__.__name__) >>> Input Source operations connected to node center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/conv2d/Conv2D: In[0] center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/zero_padding2d/Pad (defined at /usr/local/lib/python3.7/dist-packages/keras/backend.py:3672) In[1] center_net_hourglass_feature_extractor/hourglass_network/input_downsample_block/convolutional_block/conv2d/Conv2D/ReadVariableOp: Operation defined at: (most recent call last) >>> File "/usr/lib/python3.7/threading.py", line 890, in _bootstrap >>> self._bootstrap_inner() >>> >>> File "/usr/lib/python3.7/threading.py", line 926, in _bootstrap_inner >>> self.run() >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/model_lib_v2.py", line 593, in train_step_fn >>> loss = eager_train_step( >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/model_lib_v2.py", line 253, in eager_train_step >>> losses_dict, _ = _compute_losses_and_predictions_dicts( >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/model_lib_v2.py", line 118, in _compute_losses_and_predictions_dicts >>> prediction_dict = model.predict( >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/meta_architectures/center_net_meta_arch.py", line 2847, in predict >>> features_list = self._feature_extractor(preprocessed_inputs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/center_net_hourglass_feature_extractor.py", line 53, in call >>> return self._network(inputs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 431, in call >>> if self.initial_downsample: >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 432, in call >>> inputs = self.downsample_input(inputs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 174, in call >>> return self.residual_block(self.conv_block(inputs)) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/object_detection/models/keras_models/hourglass_network.py", line 94, in call >>> net = self.conv(net) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py", line 1083, in __call__ >>> outputs = call_fn(inputs, *args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 92, in error_handler >>> return fn(*args, **kwargs) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/layers/convolutional.py", line 246, in call >>> outputs = self.convolution_op(inputs, self.kernel) >>> >>> File "/usr/local/lib/python3.7/dist-packages/keras/layers/convolutional.py", line 238, in convolution_op >>> name=self.__class__.__name__) >>> Function call stack: _dist_train_step -> _dist_train_step

위의 에러가 발생합니다.

tensorflow 버전 변경 및 cuda 버전을 바꾸는등 해보는데 해결이 안되네요....