[4.1] UNet [DP, Attn, ReLU]

[gauravkuppa]

Description

Explain why we're running this and what we expect.
Make uprelu and downrelu with ReLU
Establish baseline, if ReLU is different than (ReLU, LeakyReLU) combination

Planned Start Date: 9/9/20

Depends on Previous Experiment? N

Train Command

python train.py \
--name vanilla_dp_unet_attn_relu \
--model unet \
--batch 4 \
--person_inputs densepose agnostic \
--cloth_inputs cloth \
--val_check_interval 0.05 \
--self_attn \
--accumulated_batches 16 \
--activation relu

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 -->

• Open GitHub Issue
• Start training with tmux (tensorboard and training)
• Upload scalars, train, and validation images to GitHub
• Upload checkpoints to Google Drive
• Generate test results from latest epoch
• Calculate metrics (PSNR, SSIM)
• Visualize metrics

[gauravkuppa]

Result Description

Experiment Number: 4.1.0
Branch: master
Timestamp: 09/11/2020 7pm PT
Epochs: 9.5

Architecture

Model Layers:

Module Parameters:

Loss Graphs

Image Results

Comments, Observations, or Insights

Results similar to UNet with ReLU and LeakyReLU
Specifying ReLU makes UNet network only use ReLU layers

[gauravkuppa]

Experiment 4.1.1 Fixed #115

Train Command

python train.py \
--model unet \
--batch 16 \
--person_inputs densepose agnostic \
--cloth_inputs cloth \
--val_check_interval 0.05 \
--self_attn \
--accumulated_batches 4 \
-j 12 \
--activation relu \
--name 4.1.1 \
--vvt_dataroot ~/data/fw_gan_vvt

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 -->

• Open GitHub Issue
• Start training with tmux (tensorboard and training)
• Upload scalars, train, and validation images to GitHub
• Upload checkpoints to Google Drive
• Generate test results from latest epoch
• Calculate metrics (PSNR, SSIM)
• Visualize metrics