[2.2] SAMS Generator, WITH adversarial loss, on 1-of-total frames

[gauravkuppa]

Description

Explain why we're running this and what we expect. Testing multiple frames Testing training with one frame? Early Stop: ?

Planned Start Date: 9/4/2020

Depends on Previous Experiment? Y/N Yes, depends on (Experiment 2.1)[https://github.com/andrewjong/2021-wacv-video-vton/issues/82] Follow Up Experiment 2.3

Train Command

"python train.py \
--name ""SAMS-GAN_with-adversarial-loss_1-of-total-frames"" \
--model sams \
--gpu_ids 0,1,2,3,4,5,6,7 \
--ngf_power_start 6 \
--ngf_power_end 10 \
--n_frames_total 1 \
--n_frames_now 1 \
--batch_size MAX \
--workers 8 \
--wt_multiscale 0.05 --wt_temporal 0.001
"

Report Results

To report a result, copy this into a comment below:

# Result Description
<!--- 
For Experiment Number, use "Major.minor.patch", e.g. 1.2.0.
Major.minor should match the [M.m] in the title. 
Patch describes a bug fix (change in the code or branch).
-->
**Experiment Number:** 1.2.0
**Branch:** `master`
**Timestamp:** MM/DD/YYYY 9pm PT
**Epochs:** 

# Architecture
**Model Layers:**
<!-- Paste the printed Model Layers -->

**Module Parameters:**
<!-- Paste the Params table -->

# Loss Graphs
<!--- Put detailed loss graphs here. Please include all graphs! -->

# Image Results
<!--- Put detailed image results here. Please include all images! Multiple screenshots is good. -->

# Comments, Observations, or Insights
<!--- Optional -->

[gauravkuppa]

Oops, accidentally closed! This is still open :+1: