toni-heittola / dcase2020_task1_baseline Goto Github PK

Unable to open file (unable to open file: name = '/dcase2020/dcase2020_task1_baseline/system/task1a/learner/data_processing_chain_9f195446c46cc0b161f03c4578ad7b3d/learner_2d8800654b8df776abbcc53518c40084/model_fold_1.h5'

need I go to download it manually? or it is not available now?
thX!

when I run task1a, it reported the following error：

[E] Uncaught exception (logging.py:221)
Traceback (most recent call last):
File "task1a.py", line 1297, in
sys.exit(main(sys.argv))
File "task1a.py", line 206, in main
processed_items = do_learning(
File "task1a.py", line 680, in do_learning
dcase_util.keras.setup_keras(
File "/root/anaconda3/lib/python3.8/site-packages/dcase_util/decorators/decorators.py", line 14, in call
return self.f(*args, **kwargs)
File "/root/anaconda3/lib/python3.8/site-packages/dcase_util/keras/utils.py", line 302, in setup_keras
config = tf.ConfigProto(
AttributeError: module 'tensorflow' has no attribute 'ConfigProto'

Package version:
dcase_util 0.2.12 / dcase_util 0.2.16
keras 2.4.3
tensorflow 2.3.1
Python 3.7.4

I found that it may caused by the mismatched package version, so I installed tensorflow==1.14.0. And then another error was reported. It is shown as following:
Traceback (most recent call last):
File "task1a.py", line 1297, in
sys.exit(main(sys.argv))
File "task1a.py", line 211, in main
overwrite=overwrite
File "task1a.py", line 860, in do_learning
shuffle=param.get_path('learner.parameters.fit.shuffle')
File "/usr/local/python3/lib/python3.7/site-packages/keras/engine/training.py", line 1178, in fit
validation_freq=validation_freq)
File "/usr/local/python3/lib/python3.7/site-packages/keras/engine/training_arrays.py", line 200, in fit_loop
callbacks._call_batch_hook('train', 'begin', batch_index, batch_logs)
File "/usr/local/python3/lib/python3.7/site-packages/keras/callbacks.py", line 84, in _call_batch_hook
batch_hook = getattr(callback, hook_name)
AttributeError: 'ProgressLoggerCallback' object has no attribute 'on_train_batch_begin'

I also tried other suggestions for these problems, but it can't be solved. I appreciate if you can give me some suggestions.

Traceback (most recent call last): File "task1b.py", line 692, in <module> sys.exit(main(sys.argv)) File "task1b.py", line 233, in main overwrite=overwrite File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/at007484/code/Users/dcase2020_task1_baseline-master/task1a.py", line 637, in do_learning init_parameters=init_parameters, File "/anaconda/envs/tf-dcase-old/lib/python3.7/site-packages/dcase_util/processors/processing_chain.py", line 359, in push_processor 'output_type': output_type, File "/anaconda/envs/tf-dcase-old/lib/python3.7/site-packages/dcase_util/processors/processing_chain.py", line 27, in __init__ self.init_processor_class() File "/anaconda/envs/tf-dcase-old/lib/python3.7/site-packages/dcase_util/processors/processing_chain.py", line 54, in init_processor_class self.processor_class = eval('processor_module.' + processor_name.split('.')[-1])(**processor_init_parameters) File "/anaconda/envs/tf-dcase-old/lib/python3.7/site-packages/dcase_util/processors/data.py", line 448, in __init__ normalizer = Normalizer().load(filename=filename) File "/anaconda/envs/tf-dcase-old/lib/python3.7/site-packages/dcase_util/containers/containers.py", line 64, in load self.__dict__.update(Serializer.load_cpickle(filename=self.filename)) File "/anaconda/envs/tf-dcase-old/lib/python3.7/site-packages/dcase_util/files/serialization.py", line 122, in load_cpickle return pickle.load(open(filename, "rb")) ValueError: unsupported pickle protocol: 5

when trying
python3 task1b.py -m eval -o output.csv

The evaluation script saves an empty CSV file and doesn't print any evaluation results

i tried to use cnn but got this error

File "/usr/local/lib/python3.6/dist-packages/dcase_util/keras/data.py", line 507, in data_collector
for i in range(0, data.shape[data.sequence_axis]):
AttributeError: 'FeatureContainer' object has no attribute 'sequence_axis'

I try the extra.yaml for example 2 or 3.

python task1b.py -p extra.yaml

then I got

[I]   Collecting training data
[E] Uncaught exception  (logging.py:221)
Traceback (most recent call last):
  File "task1b.py", line 692, in <module>
    sys.exit(main(sys.argv))
  File "task1b.py", line 233, in main
    overwrite=overwrite
  File "/home/sysadmin/AILabs/dcase2020_task1_baseline/task1a.py", line 754, in do_learning
    print_indent=4
  File "/home/sysadmin/anaconda3/envs/dcase2020_tf1/lib/python3.7/site-packages/dcase_util/keras/data.py", line 507, in data_collector
    for i in range(0, data.shape[data.sequence_axis]):
AttributeError: 'FeatureContainer' object has no attribute 'sequence_axi

But it stopped with the following error.
What would be the cause?

Also how does extra.yaml work?
(Does it work on the top on task1a.yaml or task1b.yaml?)

ex.2

active_set: baseline-minified
sets:
  - set_id: baseline-minified
    description: Minified DCASE2020 baseline subtask B minified
    learner_method_parameters:
      cnn:
        model:
          constants:
            CONVOLUTION_KERNEL_SIZE: 3            
    
          config:
            - class_name: Conv2D
              config:
                input_shape:
                  - FEATURE_VECTOR_LENGTH   # data_axis
                  - INPUT_SEQUENCE_LENGTH   # time_axis
                  - 1                       # sequence_axis
                filters: 8
                kernel_size: CONVOLUTION_KERNEL_SIZE
                padding: CONVOLUTION_BORDER_MODE
                kernel_initializer: CONVOLUTION_INIT
                data_format: DATA_FORMAT
            - class_name: Activation
              config:
                activation: CONVOLUTION_ACTIVATION
            - class_name: MaxPooling2D
              config:
                pool_size:
                  - 5
                  - 5
                data_format: DATA_FORMAT
            - class_name: Conv2D
              config:
                filters: 16
                kernel_size: CONVOLUTION_KERNEL_SIZE
                padding: CONVOLUTION_BORDER_MODE
                kernel_initializer: CONVOLUTION_INIT
                data_format: DATA_FORMAT
            - class_name: Activation
              config:
                activation: CONVOLUTION_ACTIVATION
            - class_name: MaxPooling2D
              config:
                pool_size:
                  - 4
                  - 100
                data_format: DATA_FORMAT
            - class_name: Flatten      
            - class_name: Dense
              config:
                units: 100
                kernel_initializer: uniform
                activation: relu    
            - class_name: Dense
              config:
                units: CLASS_COUNT
                kernel_initializer: uniform
                activation: softmax                        
        fit:
            epochs: 100

ex.3

active_set: baseline-kernel3
sets:
  - set_id: baseline-kernel3
    description: DCASE2020 baseline for subtask B with kernel 3
    learner_method_parameters:
      cnn:
        model:
          constants:
            CONVOLUTION_KERNEL_SIZE: 3
        fit:
          epochs: 100                    
  - set_id: baseline-kernel5
    description: DCASE2020 baseline for subtask B with kernel 5
    learner_method_parameters:
      cnn:
        model:
          constants:
            CONVOLUTION_KERNEL_SIZE: 5
        fit:
          epochs: 100

Hi @toni-heittola,

Thank you for preparing this baseline, it is very helpful.

I have a short question concerning model size calculation for Task 1B. Currently, it seems that your script counts int8 as two bytes:

It looks like a typo or shall we consider this in weighting our models for Task 1B?

Thank you in advance for clarification.

Best regards,
Michał