Feature/windows conda support

[ababilinski]

• Include a environment.yml file to help with repo installation on Windows 10
• Cuda Support
• no need to specify file type - .png and .jpg will work automagicly
• MiDaS upgraded to MiDaS v2

[lyxpuppet]

I tried "conda env create --file environment.yml", but it doesn't work correctly

[lyxpuppet]

in colab also get an error
2021-02-25 08:22:48.594185: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
running on device 0
0% 0/1 [00:00<?, ?it/s]Current Source ==> moon
Running depth extraction at 1614241370.0889313
initialize
device: cuda
Loading weights: MiDaS/model.pt
Using cache found in /root/.cache/torch/hub/facebookresearch_WSL-Images_master
0% 0/1 [00:01<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 55, in
config['MiDaS_model_ckpt'], MidasNet, MiDaS_utils, target_w=640)
File "/content/3d-photo-inpainting/MiDaS/run.py", line 31, in run_depth
model = Net(model_path, non_negative=True)
File "/content/3d-photo-inpainting/MiDaS/midas_net.py", line 47, in init
self.load(path)
File "/content/3d-photo-inpainting/MiDaS/base_model.py", line 17, in load
self.load_state_dict(parameters)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 830, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for MidasNet:
Missing key(s) in state_dict: "pretrained.layer3.6.conv1.weight", "pretrained.layer3.6.bn1.weight", "pretrained.layer3.6.bn1.bias", "pretrained.layer3.6.bn1.running_mean", "pretrained.layer3.6.bn1.running_var", "pretrained.layer3.6.conv2.weight", "pretrained.layer3.6.bn2.weight", "pretrained.layer3.6.bn2.bias", "pretrained.layer3.6.bn2.running_mean", "pretrained.layer3.6.bn2.running_var", "pretrained.layer3.6.conv3.weight", "pretrained.layer3.6.bn3.weight", "pretrained.layer3.6.bn3.bias", "pretrained.layer3.6.bn3.running_mean", "pretrained.layer3.6.bn3.running_var", "pretrained.layer3.7.conv1.weight", "pretrained.layer3.7.bn1.weight", "pretrained.layer3.7.bn1.bias", "pretrained.layer3.7.bn1.running_mean", "pretrained.layer3.7.bn1.running_var", "pretrained.layer3.7.conv2.weight", "pretrained.layer3.7.bn2.weight", "pretrained.layer3.7.bn2.bias", "pretrained.layer3.7.bn2.running_mean", "pretrained.layer3.7.bn2.running_var", "pretrained.layer3.7.conv3.weight", "pretrained.layer3.7.bn3.weight", "pretrained.layer3.7.bn3.bias", "pretrained.layer3.7.bn3.running_mean",
...........
........
size mismatch for pretrained.layer1.4.0.conv1.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]).
size mismatch for pretrained.layer1.4.0.bn1.weight: copying