Problem testing myDLC installation with testscript.py

Hi,
I´m testing my DLC installation with testscript.py and I get this error:
FileNotFoundError: File /Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-18/labeled-data/reachingvideo1short/machinelabels-iter0.h5 does not exist

Any help would be much appreciated. I´m stock!

Cheers,

Jurgi

Check whether the machinelabels-iter0.h5 file was created. Maybe it’s a permision issue? How did you run the testscript.py?

Thank you for your respond Konrad.
I´m a newbe!!!
No, the file machinelabels-iter0.h5 wasn´t created.
No idea if this is due a permission issue. I didn´t get any message about this, but I´m a newbie, so I might have missed it. (I should mention that I running all this on OS)

  1. After installing DLC:
    Jurgi@Pimientosmetroslibres-6 conda-environments % conda env create -f DLC-CPU.yaml
  2. I then downloaded the source code:
    Jurgi@Pimientosmetroslibres-6 ~ % git clone https://github.com/DeepLabCut/DeepLabCut.git
  3. Activated my conda enviroment
    Jurgi@Pimientosmetroslibres-6 ~ % source activate DLC-CPU
  4. Went into the folder
    Jurgi@Pimientosmetroslibres-6 ~ % cd DeepLabCut
    Jurgi@Pimientosmetroslibres-6 DeepLabCut % cd examples
  5. And finally run the test:
    Jurgi@Pimientosmetroslibres-6 examples % pythonw testscript.py

Any suggestions as to how to fix this would be much appreciated.
Cheers!

Jurgi

I have no experience with MacOS but maybe we can work somethiung out. Could you provide the whole traceback of the error and DLC version you have installed?

Amazing! thanks again.
I should be running the last version of DLC, as I used the command “pip install --upgrade deeplabcut” for this. However, I get an error (zsh: command not found: import) if I try to check the installed version by running import “deeplabcut deeplabcut.version

The traceback of the error would be (If I understood correctly what you meant by traceback):
Last login: Mon Feb 22 09:53:49 on ttys000
(base) Jurgi@Pimientosmetroslibres-6 ~ % git clone https://github.com/DeepLabCut/DeepLabCut.git
xcrun: error: invalid active developer path (/Library/Developer/CommandLineTools), missing xcrun at: /Library/Developer/CommandLineTools/usr/bin/xcrun
(base) Jurgi@Pimientosmetroslibres-6 ~ % source activate DLC-CPU
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 ~ % cd DeepLabCut
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 DeepLabCut % ls
AUTHORS LICENSE compile.sh dlc.py reinstall.sh tests
CODE_OF_CONDUCT.md README.md conda-environments docs requirements.txt testscript_cli.py
CONTRIBUTING.md _config.yml deeplabcut examples setup.py
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 DeepLabCut % cd examples
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 examples % pythonw testscript.py
Imported DLC!
On Windows/OSX tensorpack is not tested by default.
CREATING PROJECT
Created “/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/videos”
Created “/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/labeled-data”
Created “/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/training-datasets”
Created “/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models”
Copying the videos
/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/videos/reachingvideo1.avi
Generated “/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/config.yaml”

A new project with name TEST-Alex-2021-02-22 is created at /Users/Jurgi/DeepLabCut/examples and a configurable file (config.yaml) is stored there. Change the parameters in this file to adapt to your project’s needs.
Once you have changed the configuration file, use the function ‘extract_frames’ to select frames for labeling.
. [OPTIONAL] Use the function ‘add_new_videos’ to add new videos to your project (at any stage).
EXTRACTING FRAMES
Config file read successfully.
Extracting frames based on kmeans …
Kmeans-quantization based extracting of frames from 0.0 seconds to 8.53 seconds.
Extracting and downsampling… 256 frames from the video.
256it [00:02, 117.54it/s]
Kmeans clustering … (this might take a while)
Frames were successfully extracted, for the videos of interest.

You can now label the frames using the function ‘label_frames’ (if you extracted enough frames for all videos).
CREATING-SOME LABELS FOR THE FRAMES
Plot labels…
Creating images with labels by Alex.
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:04<00:00, 1.04it/s]
If all the labels are ok, then use the function ‘create_training_dataset’ to create the training dataset!
CREATING TRAININGSET
The training dataset is successfully created. Use the function ‘train_network’ to start training. Happy training!
CHANGING training parameters to end quickly!
TRAIN
Selecting single-animal trainer
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘alpha_r’: 0.02,
‘batch_size’: 1,
‘crop_pad’: 0,
‘cropratio’: 0.4,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘default’,
‘decay_steps’: 30000,
‘deterministic’: False,
‘display_iters’: 2,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 0.05,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘lr_init’: 0.0005,
‘max_input_size’: 1500,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘metadataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/Documentation_data-TEST_80shuffle1.pickle’,
‘min_input_size’: 64,
‘mirror’: False,
‘multi_step’: [[0.001, 5]],
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: False,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘pos_dist_thresh’: 17,
‘project_path’: ‘/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22’,
‘regularize’: False,
‘rotation’: 25,
‘rotratio’: 0.4,
‘save_iters’: 5,
‘scale_jitter_lo’: 0.5,
‘scale_jitter_up’: 1.25,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/train/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Starting with imgaug pose-dataset loader (=default).
Batch Size is 1
Initializing ResNet
Loading ImageNet-pretrained resnet_50
2021-02-22 10:04:14.308393: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2021-02-22 10:04:14.308848: I tensorflow/core/common_runtime/process_util.cc:71] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
Training parameter:
{‘stride’: 8.0, ‘weigh_part_predictions’: False, ‘weigh_negatives’: False, ‘fg_fraction’: 0.25, ‘mean_pixel’: [123.68, 116.779, 103.939], ‘shuffle’: True, ‘snapshot_prefix’: ‘/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/train/snapshot’, ‘log_dir’: ‘log’, ‘global_scale’: 0.8, ‘location_refinement’: True, ‘locref_stdev’: 7.2801, ‘locref_loss_weight’: 0.05, ‘locref_huber_loss’: True, ‘optimizer’: ‘sgd’, ‘intermediate_supervision’: False, ‘intermediate_supervision_layer’: 12, ‘regularize’: False, ‘weight_decay’: 0.0001, ‘crop_pad’: 0, ‘scoremap_dir’: ‘test’, ‘batch_size’: 1, ‘dataset_type’: ‘default’, ‘deterministic’: False, ‘mirror’: False, ‘pairwise_huber_loss’: False, ‘weigh_only_present_joints’: False, ‘partaffinityfield_predict’: False, ‘pairwise_predict’: False, ‘all_joints’: [[0], [1], [2], [3]], ‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’], ‘alpha_r’: 0.02, ‘cropratio’: 0.4, ‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’, ‘decay_steps’: 30000, ‘display_iters’: 2, ‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’, ‘lr_init’: 0.0005, ‘max_input_size’: 1500, ‘metadataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/Documentation_data-TEST_80shuffle1.pickle’, ‘min_input_size’: 64, ‘multi_step’: [[0.001, 5]], ‘net_type’: ‘resnet_50’, ‘num_joints’: 4, ‘pos_dist_thresh’: 17, ‘project_path’: ‘/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22’, ‘rotation’: 25, ‘rotratio’: 0.4, ‘save_iters’: 5, ‘scale_jitter_lo’: 0.5, ‘scale_jitter_up’: 1.25, ‘covering’: True, ‘elastic_transform’: True, ‘motion_blur’: True, ‘motion_blur_params’: {‘k’: 7, ‘angle’: [-90, 90]}}
Starting training…
iteration: 2 loss: 1.2042 lr: 0.001
iteration: 4 loss: 0.6271 lr: 0.001
2021-02-22 10:05:51.214420: W tensorflow/core/kernels/queue_base.cc:277] _0_fifo_queue: Skipping cancelled enqueue attempt with queue not closed
Exception in thread Thread-2:
Traceback (most recent call last):
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1334, in _do_call
return fn(*args)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1407, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.CancelledError: Enqueue operation was cancelled
[[{{node fifo_queue_enqueue}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/threading.py”, line 926, in _bootstrap_inner
self.run()
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/threading.py”, line 870, in run
self._target(*self._args, **self._kwargs)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py”, line 91, in load_and_enqueue
sess.run(enqueue_op, feed_dict=food)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 929, in run
run_metadata_ptr)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1152, in _run
feed_dict_tensor, options, run_metadata)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1328, in _do_run
run_metadata)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.CancelledError: Enqueue operation was cancelled
[[node fifo_queue_enqueue (defined at /Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py:77) ]]

Caused by op ‘fifo_queue_enqueue’, defined at:
File “testscript.py”, line 147, in
deeplabcut.train_network(path_config_file)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/training.py”, line 189, in train_network
allow_growth=allow_growth,
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py”, line 180, in train
batch, enqueue_op, placeholders = setup_preloading(batch_spec)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py”, line 77, in setup_preloading
enqueue_op = q.enqueue(placeholders_list)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/ops/data_flow_ops.py”, line 345, in enqueue
self._queue_ref, vals, name=scope)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/ops/gen_data_flow_ops.py”, line 4158, in queue_enqueue_v2
timeout_ms=timeout_ms, name=name)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py”, line 788, in _apply_op_helper
op_def=op_def)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py”, line 507, in new_func
return func(*args, **kwargs)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/framework/ops.py”, line 3300, in create_op
op_def=op_def)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/framework/ops.py”, line 1801, in init
self._traceback = tf_stack.extract_stack()

CancelledError (see above for traceback): Enqueue operation was cancelled
[[node fifo_queue_enqueue (defined at /Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py:77) ]]

The network is now trained and ready to evaluate. Use the function ‘evaluate_network’ to evaluate the network.
EVALUATE
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘batch_size’: 1,
‘crop_pad’: 0,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘imgaug’,
‘deterministic’: False,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 1.0,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘mirror’: False,
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: True,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘regularize’: False,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/test/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Running DLC_resnet_50_TESTFeb22shuffle1_5 with # of trainingiterations: 5
Initializing ResNet
Analyzing data…
5it [00:14, 2.99s/it]
Done and results stored for snapshot: snapshot-5
Results for 5 training iterations: 80 1 train error: 440.66 pixels. Test error: 331.01 pixels.
With pcutoff of 0.01 train error: 440.66 pixels. Test error: 331.01 pixels
Thereby, the errors are given by the average distances between the labels by DLC and the scorer.
Plotting…
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:02<00:00, 1.73it/s]
The network is evaluated and the results are stored in the subdirectory ‘evaluation_results’.
If it generalizes well, choose the best model for prediction and update the config file with the appropriate index for the ‘snapshotindex’.
Use the function ‘analyze_video’ to make predictions on new videos.
Otherwise consider retraining the network (see DeepLabCut workflow Fig 2)
CUT SHORT VIDEO AND ANALYZE (with dynamic cropping!)
/bin/sh: ffmpeg: command not found
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘batch_size’: 1,
‘crop_pad’: 0,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘imgaug’,
‘deterministic’: False,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 1.0,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘mirror’: False,
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: True,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘regularize’: False,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/test/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Using snapshot-5 for model /Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1
Starting analysis in dynamic cropping mode with parameters: (True, 0.1, 5)
Switching batchsize to 1, num_outputs (per animal) to 1 and TFGPUinference to False (all these features are not supported in this mode).
Initializing ResNet
No video(s) were found. Please check your paths and/or ‘video_type’.
analyze again…
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘batch_size’: 1,
‘crop_pad’: 0,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘imgaug’,
‘deterministic’: False,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 1.0,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘mirror’: False,
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: True,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘regularize’: False,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/test/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Using snapshot-5 for model /Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1
Initializing ResNet
No video(s) were found. Please check your paths and/or ‘video_type’.
CREATE VIDEO
No video(s) were found. Please check your paths and/or ‘video_type’.
Making plots
No videos found. Make sure you passed a list of videos and that videotype is right.
EXTRACT OUTLIERS
No suitable videos found in [’/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/videos/reachingvideo1short.avi’]
No suitable videos found in [’/Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/videos/reachingvideo1short.avi’]
RELABELING
Traceback (most recent call last):
File “testscript.py”, line 228, in
DF = pd.read_hdf(file, “df_with_missing”)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/pandas/io/pytables.py”, line 387, in read_hdf
raise FileNotFoundError(f"File {path_or_buf} does not exist")
FileNotFoundError: File /Users/Jurgi/DeepLabCut/examples/TEST-Alex-2021-02-22/labeled-data/reachingvideo1short/machinelabels-iter0.h5 does not exist
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 examples %

Finally, and I dónt know if this is related, I don’t know if this is related, but at the moment, I’m not being able to download the source code on to my computer

(base) Jurgi@Pimientosmetroslibres-6 ~ % git clone https://github.com/DeepLabCut/DeepLabCut.git

xcrun: error: invalid active developer path (/Library/Developer/CommandLineTools), missing xcrun at: /Library/Developer/CommandLineTools/usr/bin/xcrun

Many, many thanks Konrad!!

To run the git clone operation you need to make sure you have Xcode Command Line Tools installed. The easiest way is to run the following in Terminal:

xcode-select --install

Once that’s installed, you should be able to git clone. However, before you clone, it’s best to change your working directory to something like Downloads or Desktop instead of your Home directory (that’s what the ~ means before the %).
So, in Terminal:

cd ~/Desktop
git clone https://github.com/DeepLabCut/DeepLabCut.git

That will put the full folder on your Desktop, and might help with any permissions issues behind your file not found problem.

To check the version of DeeplabCut, in Terminal:
pythonw
import deeplabcut
deeplabcut.__version__
Those are double underscores around version. That should print out the version your are using.

It looks like you were trying to import depelabcut before opening a python instance, which is why you got the zsh error for import.

See if that helps, and post the results!

Dear Brando,
First of all, many, many thanks!
I followed your instructions (install Xcode Command Line Tools) and, just in case, restarted my computer.
I downloaded the DeepLabCut folder to my Desktop and run the analysis from it (meaning the new folder in Desktop), but I continue getting an error message (see below).

By the way, the version I´m running is Python 3.4.0 (default, Aug 31 2020, 07:22:35)

Cheers!!!

(base) Jurgi@Pimientosmetroslibres-6 ~ % cd ~/Desktop
(base) Jurgi@Pimientosmetroslibres-6 Desktop % git clone https://github.com/DeepLabCut/DeepLabCut.git
Cloning into ‘DeepLabCut’…
remote: Enumerating objects: 38, done.
remote: Counting objects: 100% (38/38), done.
remote: Compressing objects: 100% (31/31), done.
remote: Total 5944 (delta 16), reused 14 (delta 5), pack-reused 5906
Receiving objects: 100% (5944/5944), 146.87 MiB | 5.26 MiB/s, done.
Resolving deltas: 100% (4040/4040), done.
Updating files: 100% (363/363), done.
(base) Jurgi@Pimientosmetroslibres-6 Desktop % cd –
(base) Jurgi@Pimientosmetroslibres-6 ~ % source activate DLC-CPU
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 ~ % cd ~/Desktop
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 Desktop % cd DeepLabCut
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 DeepLabCut % cd examples
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 examples % pythonw testscript.py
Imported DLC!
On Windows/OSX tensorpack is not tested by default.
CREATING PROJECT
Created “/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/videos”
Created “/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/labeled-data”
Created “/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/training-datasets”
Created “/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models”
Copying the videos
/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/videos/reachingvideo1.avi
Generated “/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/config.yaml”

A new project with name TEST-Alex-2021-02-22 is created at /Users/Jurgi/Desktop/DeepLabCut/examples and a configurable file (config.yaml) is stored there. Change the parameters in this file to adapt to your project’s needs.
Once you have changed the configuration file, use the function ‘extract_frames’ to select frames for labeling.
. [OPTIONAL] Use the function ‘add_new_videos’ to add new videos to your project (at any stage).
EXTRACTING FRAMES
Config file read successfully.
Extracting frames based on kmeans …
Kmeans-quantization based extracting of frames from 0.0 seconds to 8.53 seconds.
Extracting and downsampling… 256 frames from the video.
256it [00:03, 76.90it/s]
Kmeans clustering … (this might take a while)
Frames were successfully extracted, for the videos of interest.

You can now label the frames using the function ‘label_frames’ (if you extracted enough frames for all videos).
CREATING-SOME LABELS FOR THE FRAMES
Plot labels…
Creating images with labels by Alex.
100%|██████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:02<00:00, 1.90it/s]
If all the labels are ok, then use the function ‘create_training_dataset’ to create the training dataset!
CREATING TRAININGSET
The training dataset is successfully created. Use the function ‘train_network’ to start training. Happy training!
CHANGING training parameters to end quickly!
TRAIN
Selecting single-animal trainer
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘alpha_r’: 0.02,
‘batch_size’: 1,
‘crop_pad’: 0,
‘cropratio’: 0.4,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘default’,
‘decay_steps’: 30000,
‘deterministic’: False,
‘display_iters’: 2,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 0.05,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘lr_init’: 0.0005,
‘max_input_size’: 1500,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘metadataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/Documentation_data-TEST_80shuffle1.pickle’,
‘min_input_size’: 64,
‘mirror’: False,
‘multi_step’: [[0.001, 5]],
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: False,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘pos_dist_thresh’: 17,
‘project_path’: ‘/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22’,
‘regularize’: False,
‘rotation’: 25,
‘rotratio’: 0.4,
‘save_iters’: 5,
‘scale_jitter_lo’: 0.5,
‘scale_jitter_up’: 1.25,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/train/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Starting with imgaug pose-dataset loader (=default).
Batch Size is 1
Initializing ResNet
Loading ImageNet-pretrained resnet_50
2021-02-22 16:02:30.311387: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2021-02-22 16:02:30.311816: I tensorflow/core/common_runtime/process_util.cc:71] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
Training parameter:
{‘stride’: 8.0, ‘weigh_part_predictions’: False, ‘weigh_negatives’: False, ‘fg_fraction’: 0.25, ‘mean_pixel’: [123.68, 116.779, 103.939], ‘shuffle’: True, ‘snapshot_prefix’: ‘/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/train/snapshot’, ‘log_dir’: ‘log’, ‘global_scale’: 0.8, ‘location_refinement’: True, ‘locref_stdev’: 7.2801, ‘locref_loss_weight’: 0.05, ‘locref_huber_loss’: True, ‘optimizer’: ‘sgd’, ‘intermediate_supervision’: False, ‘intermediate_supervision_layer’: 12, ‘regularize’: False, ‘weight_decay’: 0.0001, ‘crop_pad’: 0, ‘scoremap_dir’: ‘test’, ‘batch_size’: 1, ‘dataset_type’: ‘default’, ‘deterministic’: False, ‘mirror’: False, ‘pairwise_huber_loss’: False, ‘weigh_only_present_joints’: False, ‘partaffinityfield_predict’: False, ‘pairwise_predict’: False, ‘all_joints’: [[0], [1], [2], [3]], ‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’], ‘alpha_r’: 0.02, ‘cropratio’: 0.4, ‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’, ‘decay_steps’: 30000, ‘display_iters’: 2, ‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’, ‘lr_init’: 0.0005, ‘max_input_size’: 1500, ‘metadataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/Documentation_data-TEST_80shuffle1.pickle’, ‘min_input_size’: 64, ‘multi_step’: [[0.001, 5]], ‘net_type’: ‘resnet_50’, ‘num_joints’: 4, ‘pos_dist_thresh’: 17, ‘project_path’: ‘/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22’, ‘rotation’: 25, ‘rotratio’: 0.4, ‘save_iters’: 5, ‘scale_jitter_lo’: 0.5, ‘scale_jitter_up’: 1.25, ‘covering’: True, ‘elastic_transform’: True, ‘motion_blur’: True, ‘motion_blur_params’: {‘k’: 7, ‘angle’: [-90, 90]}}
Starting training…
iteration: 2 loss: 1.1356 lr: 0.001
iteration: 4 loss: 0.6092 lr: 0.001
2021-02-22 16:03:36.404475: W tensorflow/core/kernels/queue_base.cc:277] _0_fifo_queue: Skipping cancelled enqueue attempt with queue not closed
Exception in thread Thread-2:
Traceback (most recent call last):
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1334, in _do_call
return fn(*args)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1407, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.CancelledError: Enqueue operation was cancelled
[[{{node fifo_queue_enqueue}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/threading.py”, line 926, in _bootstrap_inner
self.run()
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/threading.py”, line 870, in run
self._target(*self._args, **self._kwargs)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py”, line 91, in load_and_enqueue
sess.run(enqueue_op, feed_dict=food)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 929, in run
run_metadata_ptr)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1152, in _run
feed_dict_tensor, options, run_metadata)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1328, in _do_run
run_metadata)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/client/session.py”, line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.CancelledError: Enqueue operation was cancelled
[[node fifo_queue_enqueue (defined at /Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py:77) ]]

Caused by op ‘fifo_queue_enqueue’, defined at:
File “testscript.py”, line 147, in
deeplabcut.train_network(path_config_file)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/training.py”, line 189, in train_network
allow_growth=allow_growth,
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py”, line 180, in train
batch, enqueue_op, placeholders = setup_preloading(batch_spec)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py”, line 77, in setup_preloading
enqueue_op = q.enqueue(placeholders_list)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/ops/data_flow_ops.py”, line 345, in enqueue
self._queue_ref, vals, name=scope)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/ops/gen_data_flow_ops.py”, line 4158, in queue_enqueue_v2
timeout_ms=timeout_ms, name=name)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py”, line 788, in _apply_op_helper
op_def=op_def)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py”, line 507, in new_func
return func(*args, **kwargs)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/framework/ops.py”, line 3300, in create_op
op_def=op_def)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/tensorflow/python/framework/ops.py”, line 1801, in init
self._traceback = tf_stack.extract_stack()

CancelledError (see above for traceback): Enqueue operation was cancelled
[[node fifo_queue_enqueue (defined at /Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/train.py:77) ]]

The network is now trained and ready to evaluate. Use the function ‘evaluate_network’ to evaluate the network.
EVALUATE
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘batch_size’: 1,
‘crop_pad’: 0,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘imgaug’,
‘deterministic’: False,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 1.0,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘mirror’: False,
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: True,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘regularize’: False,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/test/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Running DLC_resnet_50_TESTFeb22shuffle1_5 with # of trainingiterations: 5
Initializing ResNet
Analyzing data…
5it [00:17, 3.44s/it]
Done and results stored for snapshot: snapshot-5
Results for 5 training iterations: 80 1 train error: 402.45 pixels. Test error: 400.47 pixels.
With pcutoff of 0.01 train error: 402.45 pixels. Test error: 400.47 pixels
Thereby, the errors are given by the average distances between the labels by DLC and the scorer.
Plotting…
100%|██████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:03<00:00, 1.66it/s]
The network is evaluated and the results are stored in the subdirectory ‘evaluation_results’.
If it generalizes well, choose the best model for prediction and update the config file with the appropriate index for the ‘snapshotindex’.
Use the function ‘analyze_video’ to make predictions on new videos.
Otherwise consider retraining the network (see DeepLabCut workflow Fig 2)
CUT SHORT VIDEO AND ANALYZE (with dynamic cropping!)
/bin/sh: ffmpeg: command not found
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘batch_size’: 1,
‘crop_pad’: 0,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘imgaug’,
‘deterministic’: False,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 1.0,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘mirror’: False,
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: True,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘regularize’: False,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/test/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Using snapshot-5 for model /Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1
Starting analysis in dynamic cropping mode with parameters: (True, 0.1, 5)
Switching batchsize to 1, num_outputs (per animal) to 1 and TFGPUinference to False (all these features are not supported in this mode).
Initializing ResNet
No video(s) were found. Please check your paths and/or ‘video_type’.
analyze again…
Config:
{‘all_joints’: [[0], [1], [2], [3]],
‘all_joints_names’: [‘bodypart1’, ‘bodypart2’, ‘bodypart3’, ‘objectA’],
‘batch_size’: 1,
‘crop_pad’: 0,
‘dataset’: ‘training-datasets/iteration-0/UnaugmentedDataSet_TESTFeb22/TEST_Alex80shuffle1.mat’,
‘dataset_type’: ‘imgaug’,
‘deterministic’: False,
‘fg_fraction’: 0.25,
‘global_scale’: 0.8,
‘init_weights’: ‘/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/deeplabcut/pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt’,
‘intermediate_supervision’: False,
‘intermediate_supervision_layer’: 12,
‘location_refinement’: True,
‘locref_huber_loss’: True,
‘locref_loss_weight’: 1.0,
‘locref_stdev’: 7.2801,
‘log_dir’: ‘log’,
‘mean_pixel’: [123.68, 116.779, 103.939],
‘mirror’: False,
‘net_type’: ‘resnet_50’,
‘num_joints’: 4,
‘optimizer’: ‘sgd’,
‘pairwise_huber_loss’: True,
‘pairwise_predict’: False,
‘partaffinityfield_predict’: False,
‘regularize’: False,
‘scoremap_dir’: ‘test’,
‘shuffle’: True,
‘snapshot_prefix’: ‘/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1/test/snapshot’,
‘stride’: 8.0,
‘weigh_negatives’: False,
‘weigh_only_present_joints’: False,
‘weigh_part_predictions’: False,
‘weight_decay’: 0.0001}
Using snapshot-5 for model /Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/dlc-models/iteration-0/TESTFeb22-trainset80shuffle1
Initializing ResNet
No video(s) were found. Please check your paths and/or ‘video_type’.
CREATE VIDEO
No video(s) were found. Please check your paths and/or ‘video_type’.
Making plots
No videos found. Make sure you passed a list of videos and that videotype is right.
EXTRACT OUTLIERS
No suitable videos found in [’/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/videos/reachingvideo1short.avi’]
No suitable videos found in [’/Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/videos/reachingvideo1short.avi’]
RELABELING
Traceback (most recent call last):
File “testscript.py”, line 228, in
DF = pd.read_hdf(file, “df_with_missing”)
File “/Users/Jurgi/opt/anaconda3/envs/DLC-CPU/lib/python3.7/site-packages/pandas/io/pytables.py”, line 387, in read_hdf
raise FileNotFoundError(f"File {path_or_buf} does not exist")
FileNotFoundError: File /Users/Jurgi/Desktop/DeepLabCut/examples/TEST-Alex-2021-02-22/labeled-data/reachingvideo1short/machinelabels-iter0.h5 does not exist
(DLC-CPU) Jurgi@Pimientosmetroslibres-6 examples %

This can be infuriating, can’t it?

The key is this error:

Try running
conda install -c conda-forge ffmpeg from terminal after activating the env.

See here for more.

I can´t believe it, you solved it!!!
Yes, infuriating, and depressing in equal parts. I feel soo helpless not understanding this new system, but also SOOO grateful for your, and Konrad´s help. Really amazing that you came to the rescue of a total stranger.
Makes me hopeful.

Amazing!

Cheers!

Jurgi