Error while running action recognition net

Check the .yaml file and find where the checkpoint is.
Then rename it.

I read this section but where I have to make changes I am not getting

This my .yaml file:
output_dir: /root/getting_started_v4.0.1/notebooks/tao_launcher_starter_kit/action_recognition_net/actionrecognitionnet/rgb_3d_ptm
encryption_key: cXQ5NTRwMnU0YzNlMXNxNzEyNmkyb2JoMHE6ODVhMDJlMDctZTg1OC00ZmJiLThmMTUtOGVhN2Y3YTRmMmRl
model_config:
model_type: rgb
backbone: resnet18
rgb_seq_length: 3
input_type: 3d
sample_strategy: consecutive
dropout_ratio: 0.0
train_config:
optim:
lr: 0.001
momentum: 0.9
weight_decay: 0.0001
lr_scheduler: MultiStep
lr_steps: [5, 15, 20]
lr_decay: 0.1
epochs: 20
checkpoint_interval: 1
dataset_config:
train_dataset_dir: /root/getting_started_v4.0.1/notebooks/tao_launcher_starter_kit/action_recognition_net/data/actionrecognitionnet/train
val_dataset_dir: /root/getting_started_v4.0.1/notebooks/tao_launcher_starter_kit/action_recognition_net/data/actionrecognitionnet/test
label_map:
fall_floor: 0
ride_bike: 1
output_shape:

  • 224
  • 224
    batch_size: 32
    workers: 8
    clips_per_video: 5
    augmentation_config:
    train_crop_type: no_crop
    horizontal_flip_prob: 0.5
    rgb_input_mean: [0.5]
    rgb_input_std: [0.5]
    val_center_crop: False

there is no ‘=’ sign.

please help me out

Is it
image

yess

How about running with
!tao action_recognition train
-e $SPECS_DIR/train_rgb_3d_finetune.yaml
-r $RESULTS_DIR/rgb_3d_ptm
-k $KEY

I will try this and get back to you if i get the same error

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Also, please share the full command you run previously.
Above screenshot does not show the full command.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.