VictorMylle/Thesis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Changed steps in diffusion model

Browse Source
This commit is contained in:
Victor Mylle
2024-01-20 09:44:14 +00:00
parent c6fa17fa40
commit acaad2710a
6 changed files with 106 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
Result-Reports/Policies.md
View File

@@ -144,5 +144,14 @@ Test data: 01-01-2023 until 08-10–2023
- [x] Profit penalty parameter als over charge cycles voor een dag -> parameter bepalen op training data (convex probleem) (< 400 charge cycles per jaar) (over een dag kijken hoeveel charge cycles -> profit - penalty * charge cycles erover, (misschien belonen als eronder charge cycles))
- [ ] Meer verschil bekijken tussen GRU en diffusion
- [ ] Andere lagen voor diffusion model (GRU, kijken naar TSDiff)
- [x] Policies met andere modellen (Linear, Non Linear)
- [ ] (In Progress) Andere lagen voor diffusion model (GRU, kijken naar TSDiff)
- [x] Policies met andere modellen (Linear, Non Linear)
- [ ] Visualize the policies over the whole testr set -> thresholds plotten voor elke dag (elke policy) -> mss distribution om overzichtelijk te houden (mean and std)
- [ ] Probleem met diffusion model (activation function? waarom direct grote waardes?)
- [ ] Autoregressive confidence problem -> Quantiles zelf uit elkaar halen (helpt dit?)
- [ ] time steps reducing for diffusion model (UNet activation functions?)
- [ ] (State space model? S4)

5
src/models/diffusion_model.py
View File

@@ -56,7 +56,7 @@ class GRUDiffusionModel(DiffusionModel):
# GRU layer
self.gru = nn.GRU(input_size=input_size + time_dim + other_inputs_dim,
hidden_size=gru_hidden_size,
num_layers=2,
num_layers=3,
batch_first=True)
# Fully connected layers after GRU
@@ -87,7 +87,8 @@ class GRUDiffusionModel(DiffusionModel):
# Pass through GRU
output, hidden = self.gru(x) # Hidden Shape: [batch_size, seq_len, 1]
x = hidden
# Get last hidden state
x = hidden[-1]
# Process each time step's output with fully connected layers
for layer in self.fc_layers:

94
src/notebooks/diffusion-training.ipynb
View File

@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -31,7 +31,7 @@
"from datetime import datetime\n",
"import torch.nn as nn\n",
"from src.models.time_embedding_layer import TimeEmbedding\n",
"from src.models.diffusion_model import SimpleDiffusionModel\n",
"from src.models.diffusion_model import SimpleDiffusionModel, GRUDiffusionModel\n",
"from src.trainers.diffusion_trainer import DiffusionTrainer\n",
"from torchinfo import summary\n",
"\n",
@@ -62,30 +62,99 @@
"\n",
"data_config.NOMINAL_NET_POSITION = True\n",
"\n",
"data_processor = DataProcessor(data_config, path=\"../../\")\n",
"data_processor = DataProcessor(data_config, path=\"../../\", lstm=True)\n",
"data_processor.set_batch_size(1024)\n",
"data_processor.set_full_day_skip(True)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ClearML Task: created new task id=b71216825809432682ea3c7841c07612\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/b71216825809432682ea3c7841c07612/output/log\n"
"torch.Size([1024, 96, 96])\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"500 model found when searching for `file:///workspaces/Thesis/src/notebooks/checkpoint.pt`\n",
"Selected model `Autoregressive Non Linear Quantile Regression + Quarter + DoW + Net` (id=bc0cb0d7fc614e2e8b0edf5b85348646)\n"
"/opt/conda/lib/python3.10/site-packages/torch/nn/modules/loss.py:536: UserWarning: Using a target size (torch.Size([1024, 96])) that is different to the input size (torch.Size([2, 1024, 96])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.\n",
" return F.mse_loss(input, target, reduction=self.reduction)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"torch.Size([556, 96, 96])\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/lib/python3.10/site-packages/torch/nn/modules/loss.py:536: UserWarning: Using a target size (torch.Size([556, 96])) that is different to the input size (torch.Size([2, 556, 96])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.\n",
" return F.mse_loss(input, target, reduction=self.reduction)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n",
"torch.Size([1024, 96, 96])\n",
"torch.Size([556, 96, 96])\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"KeyboardInterrupt\n",
"\n"
]
}
],
@@ -95,14 +164,15 @@
"epochs=150\n",
"\n",
"#### Model ####\n",
"model = SimpleDiffusionModel(96, [512, 512, 512], other_inputs_dim=inputDim[1], time_dim=64)\n",
"# model = SimpleDiffusionModel(96, [512, 512, 512], other_inputs_dim=inputDim[1], time_dim=64)\n",
"model = GRUDiffusionModel(96, [256, 256], other_inputs_dim=inputDim[2], time_dim=64, gru_hidden_size=128)\n",
"\n",
"#### ClearML ####\n",
"task = clearml_helper.get_task(task_name=\"Diffusion Model\")\n",
"# task = clearml_helper.get_task(task_name=\"Diffusion Model\")\n",
"\n",
"#### Trainer ####\n",
"trainer = DiffusionTrainer(model, data_processor, \"cuda\")\n",
"trainer.train(epochs, learningRate, task)"
"trainer.train(epochs, learningRate, None)"
]
},
{
@@ -246,7 +316,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
"version": "3.10.8"
}
},
"nbformat": 4,

2
src/policies/plot_combiner.ipynb
View File

@@ -1197,7 +1197,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
"version": "3.10.8"
}
},
"nbformat": 4,

11
src/trainers/diffusion_trainer.py
View File

@@ -51,7 +51,7 @@ class DiffusionTrainer:
self.model = model
self.device = device
self.noise_steps = 1000
self.noise_steps = 20
self.beta_start = 1e-4
self.beta_end = 0.02
self.ts_length = 96
@@ -130,8 +130,8 @@ class DiffusionTrainer:
predict_sequence_length=self.ts_length
)
train_sample_indices = self.random_samples(train=True, num_samples=10)
test_sample_indices = self.random_samples(train=False, num_samples=10)
train_sample_indices = self.random_samples(train=True, num_samples=5)
test_sample_indices = self.random_samples(train=False, num_samples=5)
for epoch in range(epochs):
running_loss = 0.0
@@ -153,7 +153,7 @@ class DiffusionTrainer:
running_loss /= len(train_loader.dataset)
if epoch % 20 == 0 and epoch != 0:
if epoch % 40 == 0 and epoch != 0:
self.test(test_loader, epoch, task)
if task:
@@ -164,7 +164,7 @@ class DiffusionTrainer:
value=loss.item(),
)
if epoch % 100 == 0 and epoch != 0:
if epoch % 150 == 0 and epoch != 0:
self.debug_plots(task, True, train_loader, train_sample_indices, epoch)
self.debug_plots(task, False, test_loader, test_sample_indices, epoch)
@@ -177,6 +177,7 @@ class DiffusionTrainer:
features, target, _ = data_loader.dataset[idx]
features = features.to(self.device)
features = features.unsqueeze(0)
self.model.eval()
with torch.no_grad():

6
src/training_scripts/diffusion_training.py
View File

@@ -37,7 +37,7 @@ data_config.NOMINAL_NET_POSITION = True
data_config = task.connect(data_config, name="data_features")
data_processor = DataProcessor(data_config, path="", lstm=True)
data_processor = DataProcessor(data_config, path="", lstm=False)
data_processor.set_batch_size(128)
data_processor.set_full_day_skip(True)
@@ -54,8 +54,8 @@ model_parameters = {
model_parameters = task.connect(model_parameters, name="model_parameters")
#### Model ####
# model = SimpleDiffusionModel(96, model_parameters["hidden_sizes"], other_inputs_dim=inputDim[1], time_dim=model_parameters["time_dim"])
model = GRUDiffusionModel(96, model_parameters["hidden_sizes"], other_inputs_dim=inputDim[2], time_dim=model_parameters["time_dim"], gru_hidden_size=256)
model = SimpleDiffusionModel(96, model_parameters["hidden_sizes"], other_inputs_dim=inputDim[1], time_dim=model_parameters["time_dim"])
# model = GRUDiffusionModel(96, model_parameters["hidden_sizes"], other_inputs_dim=inputDim[2], time_dim=model_parameters["time_dim"], gru_hidden_size=256)
print("Starting training ...")