Skip to content
Snippets Groups Projects
Commit 3597a501 authored by Tobias Seibel's avatar Tobias Seibel
Browse files

path to data fixed

parent 7ba3be86
No related branches found
No related tags found
No related merge requests found
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
from trainer.train import * from trainer.train import *
from dataloader.load import * from dataloader.load import *
from models.Framework import * from models.Framework import *
from models.unet_unconditional_diffusion import * from models.unet_unconditional_diffusion import *
import torch import torch
from torch import nn from torch import nn
``` ```
%% Cell type:markdown id: tags: %% Cell type:markdown id: tags:
# Prepare experiment # Prepare experiment
1. Adapt settings below (for data path, only use absolute paths!!) 1. Adapt settings below (for data path, only use absolute paths!!)
2. run both cells of the notebook, this creates a folder containing the json setting files 2. run both cells of the notebook, this creates a folder containing the json setting files
2. put the folder on the HPC 2. put the folder on the HPC
3. the following command starts the training `python main.py train "<absolute path of folder in hpc>"` add it to the batch file 3. the following command starts the training `python main.py train "<absolute path of folder in hpc>"` add it to the batch file
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
import torch import torch
#path to store, path to load data , path to checkpoint #path to store, path to load data , path to checkpoint
#basic settings: #basic settings:
learning_rate = 0.0001 learning_rate = 0.0001
batchsize = 128 batchsize = 128
datapath = "work/lect0100/lhq256" datapath = "work/lect0100/lhq_256"
checkpoint_path = None #when training from checkpoint checkpoint_path = None #when training from checkpoint
experimentname = "/work/lect0100/results/" + "test1" #always change experiment name! experimentname = "/work/lect0100/results/" + "test1" #always change experiment name!
epochs = 20 epochs = 20
diffusion_steps = 500 diffusion_steps = 500
image_size = 64 image_size = 64
channels = 3 channels = 3
store_iter = 5 store_iter = 5
optimizername = "torch.optim.AdamW" optimizername = "torch.optim.AdamW"
name_appendix = 'DM_testing_0'# id for WANDB name_appendix = 'DM_testing_0'# id for WANDB
#advanced settings: change directly in dictionary #advanced settings: change directly in dictionary
meta_setting = dict(modelname = "UNet_Unconditional_Diffusion", meta_setting = dict(modelname = "UNet_Unconditional_Diffusion",
dataset = "UnconditionalDataset", dataset = "UnconditionalDataset",
framework = "DDPM", framework = "DDPM",
trainloop_function = "ddpm_trainer", trainloop_function = "ddpm_trainer",
batchsize = batchsize, batchsize = batchsize,
) )
dataset_setting = dict(fpath = datapath, dataset_setting = dict(fpath = datapath,
img_size = image_size, img_size = image_size,
frac =0.8, frac =0.8,
skip_first_n = 0, skip_first_n = 0,
ext = ".png", ext = ".png",
transform=True transform=True
) )
model_setting = dict( channels_in=channels, model_setting = dict( channels_in=channels,
channels_out =channels , channels_out =channels ,
activation='relu', # activation function. Options: {'relu', 'leakyrelu', 'selu', 'gelu', 'silu'/'swish'} activation='relu', # activation function. Options: {'relu', 'leakyrelu', 'selu', 'gelu', 'silu'/'swish'}
weight_init='he', # weight initialization. Options: {'he', 'torch'} weight_init='he', # weight initialization. Options: {'he', 'torch'}
projection_features=64, # number of image features after first convolution layer projection_features=64, # number of image features after first convolution layer
time_dim=batchsize, #dont chnage!!! time_dim=batchsize, #dont chnage!!!
time_channels=diffusion_steps, # number of time channels #TODO same as diffusion steps? time_channels=diffusion_steps, # number of time channels #TODO same as diffusion steps?
num_stages=4, # number of stages in contracting/expansive path num_stages=4, # number of stages in contracting/expansive path
stage_list=None, # specify number of features produced by stages stage_list=None, # specify number of features produced by stages
num_blocks=2, # number of ConvResBlock in each contracting/expansive path num_blocks=2, # number of ConvResBlock in each contracting/expansive path
num_groupnorm_groups=32, # number of groups used in Group Normalization inside a ConvResBlock num_groupnorm_groups=32, # number of groups used in Group Normalization inside a ConvResBlock
dropout=0.1, # drop-out to be applied inside a ConvResBlock dropout=0.1, # drop-out to be applied inside a ConvResBlock
attention_list=None, # specify MHA pattern across stages attention_list=None, # specify MHA pattern across stages
num_attention_heads=1, num_attention_heads=1,
) )
framework_setting = dict( framework_setting = dict(
diffusion_steps = diffusion_steps, # dont change!! diffusion_steps = diffusion_steps, # dont change!!
out_shape = (channels,image_size,image_size), # dont change!! out_shape = (channels,image_size,image_size), # dont change!!
noise_schedule = 'linear', noise_schedule = 'linear',
beta_1 = 1e-4, beta_1 = 1e-4,
beta_T = 0.02, beta_T = 0.02,
alpha_bar_lower_bound = 0.9, alpha_bar_lower_bound = 0.9,
var_schedule = 'same', var_schedule = 'same',
kl_loss = 'simplified', kl_loss = 'simplified',
recon_loss = 'none', recon_loss = 'none',
) )
training_setting = dict( training_setting = dict(
epochs = epochs, epochs = epochs,
store_iter = store_iter, store_iter = store_iter,
eval_iter = 3, eval_iter = 3,
optimizer_class=optimizername, optimizer_class=optimizername,
optimizer_params=dict(lr=learning_rate), # don't change! optimizer_params=dict(lr=learning_rate), # don't change!
scheduler_class= None, scheduler_class= None,
scheduler_params=None, scheduler_params=None,
last_epoch=-1, last_epoch=-1,
learning_rate = learning_rate, learning_rate = learning_rate,
lr_schedule = False, lr_schedule = False,
verbose = True, verbose = True,
name_appendix=name_appendix, name_appendix=name_appendix,
checkpoint_path= checkpoint_path, checkpoint_path= checkpoint_path,
) )
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
import os import os
import json import json
f = experimentname f = experimentname
if os.path.exists(f): if os.path.exists(f):
print("path already exists, pick a new name!") print("path already exists, pick a new name!")
print("break") print("break")
else: else:
print("create folder") print("create folder")
os.mkdir(f) os.mkdir(f)
print("folder created ") print("folder created ")
with open(f+"/meta_setting.json","w+") as fp: with open(f+"/meta_setting.json","w+") as fp:
json.dump(meta_setting,fp) json.dump(meta_setting,fp)
with open(f+"/dataset_setting.json","w+") as fp: with open(f+"/dataset_setting.json","w+") as fp:
json.dump(dataset_setting,fp) json.dump(dataset_setting,fp)
with open(f+"/model_setting.json","w+") as fp: with open(f+"/model_setting.json","w+") as fp:
json.dump(model_setting,fp) json.dump(model_setting,fp)
with open(f+"/framework_setting.json","w+") as fp: with open(f+"/framework_setting.json","w+") as fp:
json.dump(framework_setting,fp) json.dump(framework_setting,fp)
with open(f+"/training_setting.json","w+") as fp: with open(f+"/training_setting.json","w+") as fp:
json.dump(training_setting,fp) json.dump(training_setting,fp)
print("stored json files in folder") print("stored json files in folder")
print(meta_setting) print(meta_setting)
print(dataset_setting) print(dataset_setting)
print(model_setting) print(model_setting)
print(framework_setting) print(framework_setting)
print(training_setting) print(training_setting)
``` ```
%% Output %% Output
path already exists, pick a new name! path already exists, pick a new name!
break break
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment