Problem with generating fitted timelines about autovideo HOT 6 CLOSED

@viniciusarasantos Thank you for pointing out the issue. Seems like the previous link that we were using to download the weights is broken. I have modified the primitives to support loading pre-trained models from the 'weights/' directory. You can download the pre-trained weights from GoogleDrive and place it in the weights directory. Let me know if this resolves your issue.

from autovideo.

@viniciusarasantos Thank you for pointing out the issue. Seems like the previous link that we were using to download the weights is broken. I have modified the primitives to support loading pre-trained models from the 'weights/' directory. You can download the pre-trained weights from GoogleDrive and place it in the weights directory. Let me know if this resolves your issue.

Thanks. That works like a charm.

I could not run ECO-Lite and ECO-Full. Is there a fix for it?

from autovideo.

Could you share the error you are facing while running ECO-Lite and ECO-Full?

from autovideo.

Yes, I can.

I runned this command:
python3 examples/fit.py --alg eco --pretrained --gpu 0,1 --data_dir datasets/hmdb6/ --log_path logs/ECO.txt --save_path fitted_timelines/ECO.fitted

And got the following error.

--> Running on the GPU

Initializing ECO with base model: ECO.
ECO Configurations:
input_modality: RGB
num_segments: 8
new_length: 1
consensus_module: identity
dropout_ratio: 0.8

Traceback (most recent call last):
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 1008, in _do_run_step
self._run_step(step)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 998, in _run_step
self._run_primitive(step)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 873, in _run_primitive
multi_call_result = self._call_primitive_method(primitive.fit_multi_produce, fit_multi_produce_arguments)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 974, in _call_primitive_method
raise error
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 970, in _call_primitive_method
result = method(**arguments)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/primitive_interfaces/base.py", line 532, in fit_multi_produce
return self._fit_multi_produce(produce_methods=produce_methods, timeout=timeout, iterations=iterations, inputs=inputs, outputs=outputs)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/primitive_interfaces/base.py", line 559, in _fit_multi_produce
fit_result = self.fit(timeout=timeout, iterations=iterations)
File "/home/araujo/autovideo/autovideo/base/supervised_base.py", line 54, in fit
self._init_model(pretrained = self.hyperparams['load_pretrained'])
File "/home/araujo/autovideo/autovideo/recognition/eco_primitive.py", line 243, in _init_model
new_state_dict = init_ECO(model_dict, self.model.pretrained_parts)
File "/home/araujo/autovideo/autovideo/recognition/eco_primitive.py", line 321, in init_ECO
pretrained_dict_2d = torch.load(pretrained_path_2d)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/torch/serialization.py", line 596, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/torch/serialization.py", line 232, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/torch/serialization.py", line 213, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'weights/bninception_rgb_kinetics_init-d4ee618d3399.pth'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "examples/fit.py", line 61, in
run(args)
File "examples/fit.py", line 49, in run
pipeline=pipeline)
File "/home/araujo/autovideo/autovideo/utils/axolotl_utils.py", line 55, in fit
raise pipeline_result.error
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 1039, in _run
self._do_run()
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 1025, in _do_run
self._do_run_step(step)
File "/home/araujo/anaconda3/envs/autovideo/lib/python3.6/site-packages/d3m/runtime.py", line 1017, in _do_run_step
) from error
d3m.exceptions.StepFailedError: Step 5 for pipeline dc954012-52d3-45d1-973f-b1ed3d00032e failed.

Was it supposed to always look for the weights in the weights directory or sometimes download it as it happens for TSN and TSM?

from autovideo.

@viniciusarasantos You have used the flag --pretrained which indicates that it will need to load the pretrianed weights. You can either remove the flag or download the weights from Google Drive and put them in the corresponding folder.

from autovideo.

@viniciusarasantos You have used the flag --pretrained which indicates that it will need to load the pretrianed weights. You can either remove the flag or download the weights from Google Drive and put them in the corresponding folder.

Oh, that makes sense. Thanks.

from autovideo.