move create_data.py to root dir

MengHao666 · Jun 16, 2021 · 9a5d1e6 · 9a5d1e6
1 parent ab4fd2d
commit 9a5d1e6
Show file tree

Hide file tree

Showing 21 changed files with 13 additions and 1,289 deletions.
diff --git a/README.md b/README.md
@@ -38,7 +38,7 @@ Offical project link:
 
 * 2021/03/24 Fixed some errors in calculating AUC. Update the 3D PCK AUC Diffenence.
 
-* 2021/06/14 A new method to estimate shape parameters by using fully connected neural network is added. Refer to [ShapeNet.md](./ShapeNet.md) for details. Thanks to kishan1823 and EEWenbinWu for pointing out the mistake. There are a little differences between the manopth I used and the official manopth. More details see [issues 11](https://github.com/MengHao666/Minimal-Hand-pytorch/issues/11)
+* 2021/06/14 A new method to estimate shape parameters by using fully connected neural network is added. Refer to [ShapeNet.md](./ShapeNet.md) for details. Thanks to kishan1823 and EEWenbinWu for pointing out the mistake. There are a little differences between the manopth I used and the official manopth. More details see [issues 11](https://github.com/MengHao666/Minimal-Hand-pytorch/issues/11). manopth/rotproj.py is the  rotproj.py which I have modified.
 
 
 ## Usage

diff --git a/ShapeNet.md b/ShapeNet.md
@@ -1,25 +1,27 @@
 ## ShapeNet
 
-#### about train ShapeNet
-ShapeNet is a model that uses fully connected neural network to estimate shape parameters. Code of ShapeNet are adapted from [bihand](https://github.com/lixiny/bihand). If you want train your ShapeNet, just run these. 
+#### train ShapeNet
+
+ShapeNet is a model that uses fully connected neural network to estimate shape parameters.  It's faster than pso. Code of ShapeNet are adapted from [bihand](https://github.com/lixiny/bihand). If you want train your ShapeNet, just run these. 
 
 ```python
-# to create training set
-python utils/create_data.py
+# create training set
+python create_data.py
 # train the model
 python train_shape_net.py
 ```
-   As for the pre-trained model, you can download from 需要添加连接.
+   As for the pre-trained model or the trainingset generated by me, you can download from 需要添加连接.
+
+#### training set
 
-#### about training set 
-   The training set is generated by MANO. More details see utils/create_data.py.
+   The training set is generated by MANO. More details see create_data.py.
 
 1. First sample shape parameters from normal distribution N(0,3)
 
 2. Calculate the relative bone length corresponding to the shape parameter.
 
+#### loss
 
-#### about loss 
    The loss of ShapeNet consists of two parts, one is the error of relative bone length, the other is the regularization loss of shape parameters.
 
 $$
@@ -32,8 +34,8 @@ $$
 
       In my opinion, shape parameters include not only relative bone length information, but also absolute bone length information. It is impossible to          guarantee that a relative bone length only corresponds to one shape parameter, which is necessary for neural networks. Therefore, the loss function does not directly calculate the error between the shape parameter and the label of it.
 
+#### AUC
 
-#### about AUC
 AUC of ShapeNet can refer [README.md](./README.md). You can get higher AUC, if you change " beta = torch.tanh(beta) " which is the line 85 of model/shape_net.py to  "beta = 3*torch.tanh(beta) ". This will make the output range of ShapeNet bigger and get higher AUC. According to the experiment, the finger will be thinner.
 
 I didn't adjust the parameters carefully. Maybe you can get better results if you adjust parameters.

diff --git a/utils/create_data.py → create_data.py b/utils/create_data.py → create_data.py
diff --git a/dl_shape_estimate.py b/dl_shape_estimate.py
@@ -2,7 +2,7 @@
 
 import torch
 
-from utils import create_data
+import create_data
 from model import shape_net
 
 import numpy as np

diff --git a/mano/__init__.py b/mano/__init__.py
diff --git a/mano/models/LICENSE.txt b/mano/models/LICENSE.txt
diff --git a/mano/models/info.txt b/mano/models/info.txt
diff --git a/mano/webuser/__init__.py b/mano/webuser/__init__.py
diff --git a/mano/webuser/lbs.py b/mano/webuser/lbs.py
diff --git a/mano/webuser/posemapper.py b/mano/webuser/posemapper.py
diff --git a/mano/webuser/serialization.py b/mano/webuser/serialization.py