Adding environment requirements

Author: MichaelRamamonjisoa

KITTI/trainer.py

@@ -26,8 +26,6 @@
 
 import datasets
 
-from IPython import embed
-
 
 class Trainer:
     def __init__(self, options):

NYUv2/model.py

@@ -35,11 +35,16 @@ def __init__(self, opts):
         self.use_sparse = False
 
         if opts.use_wavelets:
-            if opts.use_sparse:
-                self.use_sparse = True
-                if opts.use_224:
-                    raise NotImplementedError
+            try:
+                if opts.use_sparse:
+                    self.use_sparse = True
+                    if opts.use_224:
+                        raise NotImplementedError
+            except AttributeError:
+                opts.use_sparse = False
+                self.use_sparse = False
 
+            if opts.use_sparse:
                 self.decoder = SparseDecoderWave(enc_features=self.encoder.num_ch_enc, decoder_width=decoder_width)
             else:
                 if opts.use_224:

README.md

@@ -38,6 +38,24 @@ are then replaced with **sparse** ones.
 
 This is because the network first needs to learn to predict sparse wavelet coefficients before we can use sparse convolutions.
 
+## 🗂 Environment Requirements 🗂 ##
+
+We recommend creating a new Anaconda environment to use WaveletMonoDepth. Use the following to setup a new environment:
+
+```
+conda env create -f environment.yml
+conda activate wavelet-mdp
+```
+
+Our work uses [Pytorch Wavelets](https://github.com/fbcotter/pytorch_wavelets), a great package from Fergal Cotter 
+which implements the Inverse Discrete Wavelet Transform (IDWT) used in our work, and a lot more! 
+To install Pytorch Wavelets, simply run:
+```
+git clone https://github.com/fbcotter/pytorch_wavelets
+cd pytorch_wavelets
+pip install .
+```
+
 ## 🚗🚦 KITTI 🌳🛣  
 [Depth Hints](https://github.com/nianticlabs/depth-hints) was used as a baseline for KITTI.
 

environment.yml

@@ -0,0 +1,17 @@
+name: wavelet-mdp
+channels:
+  - default
+  - pytorch
+  - conda-forge
+dependencies:
+  - opencv=3.4.2
+  - matplotlib=3.1.2
+  - numpy=1.19.5
+  - scikit-learn=0.24.2
+  - pip
+  - pip:
+    - Pillow==6.2.1
+    - tensorboardX==1.5
+    - scikit-image==0.16.2
+    - torch==1.7.1
+    - torchvision==0.8.2