NOTE: This is not an official implementation. Original paper is DeepPose: Human Pose Estimation via Deep Neural Networks.
This is implementation of DeepPose (stg-1).
Code includes training and testing on 2 popular Pose Benchmarks: LSP Extended Dataset and MPII Human Pose Dataset.
Performance of Alexnet pretrained on Imagenet and finetuned on LSP is close to the performance reported in the original paper.
For tensorflow version 0.11.0rc0 and 0.12.0rc0 checkout branch r0.12
Requires around 10 Gb of free RAM.
pip
.pip install chainer numpy opencv tqdm
scripts/config.py
set ROOT_DIR
to point to the root dir of the project.weights/
dir.cd datasets
bash download.sh
cd ..
python datasets/lsp_dataset.py
python datasets/mpii_dataset.py
examples/ provide several scripts for training on LSP + LSP_EXT and MPII:
Example: bash examples/train_lsp_alexnet_scratch.sh
All these scripts call train.py
.
To check which options it accepts and which default values are set, please look into cmd_options.py
.
0.0005
as specified in the paper. scripts/regressionnet.py
in create_regression_net
method.The network wiil be tested during training and you will see the following output every T iterations:
8it [00:06, 1.31it/s]
Step 0 test/pose_loss = 0.116
Step 0 test/mPCP 0.005
Step 0 test/parts_PCP:
Head Torso U Arm L Arm U Leg L Leg mean
0.000 0.015 0.001 0.003 0.013 0.001 0.006
Step 0 test/mPCKh 0.029
Step 0 test/mSymmetricPCKh 0.026
Step 0 test/parts_mSymmetricPCKh:
Head Neck Shoulder Elbow Wrist Hip Knee Ankle
0.003 0.016 0.019 0.043 0.044 0.028 0.053 0.003
Here you can see that PCP and PCKh scores at step (iteration) 0.
test/METRIC_NAME
means that the metric was calculated on test set.
val/METRIC_NAME
means that the metric was calculated on validation set. Just for sanity check on LSP I took the first 1000 images from train as validation.
pose_loss
is the regression loss of the joint prediction,
mPCP
is mean PCP@0.5 score over all sticks,
parts_PCP
is PCP@0.5 score for every stick.
mRelaxedPCP
is a relaxed PCP@0.5 score, where the stick has a correct position when the average error for both joints is less than the threshold (0.5).
mPCKh
is mean PCKh score for all joints,
mSymmetricPCKh
is mean PCKh score for all joints, where the score for symmetric left/right joints was averaged,
To test the model use tests/test_snapshot.py
.
Usage: python tests/test_snapshot.py DATASET_NAME SNAPSHOT_PATH
,
DATASET_NAME
is 'lsp'
or 'mpii'
, SNAPSHOT_PATH
is the path to the snapshot. Example: python tests/test_snapshot.py lsp out/lsp_alexnet_scratch/checkpoint-10000
Results for Random initialization and Alexnet initialization from our CVPR 2017 paper Deep Unsupervised Similarity Learning using Partially Ordered Sets. Check the paper for more results using our initialization and Shuffle&Learn initialization.
Random Init. | Alexnet | |
---|---|---|
Torso | 87.3 | 92.8 |
Upper legs | 52.3 | 68.1 |
Lower legs | 35.4 | 53.0 |
Upper arms | 25.4 | 39.8 |
Lower arms | 7.6 | 17.5 |
Head | 44.0 | 62.8 |
Total | 42.0 | 55.7 |
Random Init. | Alexnet | |
---|---|---|
Head | 79.5 | 87.2 |
Neck | 87.1 | 93.2 |
LR Shoulder | 71.6 | 85.2 |
LR Elbow | 52.1 | 69.6 |
LR Wrist | 34.6 | 52.0 |
LR Hip | 64.1 | 81.3 |
LR Knee | 58.3 | 69.7 |
LR Ankle | 51.2 | 62.0 |
Thorax | 85.5 | 93.4 |
Pelvis | 70.1 | 86.6 |
Total | 65.4 | 78.0 |
If you use this code please cite the repo.
GNU General Public License