ValueError: Unable to retrieve parameter 'w' when trying to use `eval_inference`

[jeremyrcoyle]

When invoking experiment.py to do inference:

python3 ./tapnet/experiment.py \
  --config=./tapnet/configs/tapnet_config.py \
  --jaxline_mode=eval_inference \
  --config.checkpoint_dir=./tapnet/checkpoint/ \
  --config.experiment_kwargs.config.inference.input_video_path=fixed10.mp4 \
  --config.experiment_kwargs.config.inference.output_video_path=result.mp4 \
  --config.experiment_kwargs.config.inference.resize_height=256 \
  --config.experiment_kwargs.config.inference.resize_width=256 \
  --config.experiment_kwargs.config.inference.num_points=20

I get the following error:

Traceback (most recent call last):
  File "./tapnet/experiment.py", line 431, in <module>
    app.run(main)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/absl/app.py", line 308, in run
    _run_main(main, args)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/absl/app.py", line 254, in _run_main
    sys.exit(main(argv))
  File "./tapnet/experiment.py", line 424, in main
    platform.main(
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/jaxline/utils.py", line 484, in inner_wrapper
    return f(*args, **kwargs)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/jaxline/platform.py", line 137, in main
    train.evaluate(experiment_class, config, checkpointer, writer,
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/jaxline/utils.py", line 620, in inner_wrapper
    return fn(*args, **kwargs)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/jaxline/train.py", line 225, in evaluate
    scalar_values = utils.evaluate_should_return_dict(experiment.evaluate)(
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/jaxline/utils.py", line 521, in evaluate_with_warning
    evaluate_out = f(*args, **kwargs)
  File "./tapnet/experiment.py", line 405, in evaluate
    eval_scalars = point_prediction_task.evaluate(
  File "/home/jrcoyle/tapnet/supervised_point_prediction.py", line 370, in evaluate
    self._eval_inference(
  File "/home/jrcoyle/tapnet/supervised_point_prediction.py", line 981, in _eval_inference
    outputs, _ = self._infer_batch(
  File "/home/jrcoyle/tapnet/supervised_point_prediction.py", line 440, in _infer_batch
    output, _ = functools.partial(wrapped_forward_fn, input_key=input_key)(
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/transform.py", line 357, in apply_fn
    out = f(*args, **kwargs)
  File "./tapnet/experiment.py", line 125, in forward
    return self.point_prediction.forward_fn(
  File "/home/jrcoyle/tapnet/supervised_point_prediction.py", line 150, in forward_fn
    return shared_modules[self.model_key](
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/module.py", line 426, in wrapped
    out = f(*args, **kwargs)
  File "/usr/lib/python3.8/contextlib.py", line 75, in inner
    return func(*args, **kwds)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/module.py", line 272, in run_interceptors
    return bound_method(*args, **kwargs)
  File "/home/jrcoyle/tapnet/tapnet_model.py", line 215, in __call__
    latent = self.tsm_resnet(
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/module.py", line 426, in wrapped
    out = f(*args, **kwargs)
  File "/usr/lib/python3.8/contextlib.py", line 75, in inner
    return func(*args, **kwds)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/module.py", line 272, in run_interceptors
    return bound_method(*args, **kwargs)
  File "/home/jrcoyle/tapnet/models/tsm_resnet.py", line 383, in __call__
    net = hk.Conv2D(
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/module.py", line 426, in wrapped
    out = f(*args, **kwargs)
  File "/usr/lib/python3.8/contextlib.py", line 75, in inner
    return func(*args, **kwds)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/module.py", line 272, in run_interceptors
    return bound_method(*args, **kwargs)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/conv.py", line 200, in __call__
    w = hk.get_parameter("w", w_shape, inputs.dtype, init=w_init)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/base.py", line 448, in wrapped
    return wrapped._current(*args, **kwargs)
  File "/home/jrcoyle/.local/lib/python3.8/site-packages/haiku/_src/base.py", line 524, in get_parameter
    raise ValueError(
ValueError: Unable to retrieve parameter 'w' for module 'tap_net/~/tsm_resnet_video/tsm_resnet_stem' All parameters must be created as part of `init`.

Attempting to use a local GPU. The live_demo.py script works for me, so not sure what the issue is here.

[cdoersch]

live_demo.py uses a TAPIR model, but it looks like you're using a TAP-Net config. What checkpoint file are you trying to use with that code? Did you perhaps intend to use a TAPIR config?

[jeremyrcoyle]

I'm using the checkpoint from https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.

[jeremyrcoyle]

Please let me know if there is any more info I can provide or debugging steps on my end.

[cdoersch]

Is it an option to use the code snippet we provide for inference in the colab?

Has the error message changed from using the tapir config? The traceback you provided above has tap_net/ as the prefix for the variable names; it should be tapir if you're actually running a tapir model. Without more information it's difficult to guess why that's happening.

[wenshengyoung]

Did you solve the problem, I had the same thing happen to me.

[ldg810]

I am getting same error... Is there any solution??

[ldg810]

I am getting same error... Is there any solution??

I found the problem. you shoud have checkpoint.npy file in checkpoint path.

wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy

[cdalinghaus]

I am getting same error... Is there any solution??

I found the problem. you shoud have checkpoint.npy file in checkpoint path.

wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy

Also, this is a different checkpoint than in

I'm using the checkpoint from https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.

Using https://storage.googleapis.com/dm-tapnet/checkpoint.npy, I got it to work with the experiment script.

[nutsintheshell]

I am getting same error... Is there any solution??

I found the problem. you shoud have checkpoint.npy file in checkpoint path.

wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy

Also, this is a different checkpoint than in

I'm using the checkpoint from https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.

Using https://storage.googleapis.com/dm-tapnet/checkpoint.npy, I got it to work with the experiment script.

I try your method.But another error occurs: Traceback (most recent call last): File "/home/jishengyin/anaconda3/envs/tapnet/lib/python3.10/site-packages/numpy/lib/npyio.py", line 465, in load return pickle.load(fid, **pickle_kwargs) _pickle.UnpicklingError: invalid load key, '-'.

[nutsintheshell]

I am getting same error... Is there any solution??

I found the problem. you shoud have checkpoint.npy file in checkpoint path.

wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy

Also, this is a different checkpoint than in

I'm using the checkpoint from https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.

Using https://storage.googleapis.com/dm-tapnet/checkpoint.npy, I got it to work with the experiment script.

I would like to evaluate a model. evaluation means first train a model and then evaluate it in evaluation dataset.(maybe).It means it doesn't need a pretrained model.So I can't understand why I got the error.