DCGAN.Lightning/modules/Generators.py

+
+# ------------------------------------------------------------------
+#     _____ _     _ _
+#    |  ___(_) __| | | ___
+#    | |_  | |/ _` | |/ _ \
+#    |  _| | | (_| | |  __/
+#    |_|   |_|\__,_|_|\___|                         GAN / Generators
+# ------------------------------------------------------------------
+# Formation Introduction au Deep Learning  (FIDLE)
+# CNRS/MIAI - https://fidle.cnrs.fr
+# ------------------------------------------------------------------
+# JL Parouty (Mars 2024)
+
+
+
+import numpy as np
+import torch.nn as nn
+
+
+# -----------------------------------------------------------------------------
+# -- Generator n°1
+# -----------------------------------------------------------------------------
+#
+class Generator_1(nn.Module):
+
+    def __init__(self, latent_dim=None, data_shape=None):
+        super().__init__()
+        self.latent_dim = latent_dim
+        self.img_shape  = data_shape
+        print('init generator 1         : ',latent_dim,' to ',data_shape)
+
+        self.model = nn.Sequential(
+            
+            nn.Linear(latent_dim, 128),
+            nn.ReLU(),
+
+            nn.Linear(128,256),
+            nn.BatchNorm1d(256, 0.8),
+            nn.ReLU(),
+
+            nn.Linear(256, 512),
+            nn.BatchNorm1d(512, 0.8),
+            nn.ReLU(),
+
+            nn.Linear(512, 1024),
+            nn.BatchNorm1d(1024, 0.8),
+            nn.ReLU(),
+
+            nn.Linear(1024, int(np.prod(data_shape))),
+            nn.Sigmoid()
+
+        )
+
+    def forward(self, z):
+        img = self.model(z)
+        img = img.view(img.size(0), *self.img_shape)
+        return img
+
+
+# -----------------------------------------------------------------------------
+# -- Generator n°1
+# -----------------------------------------------------------------------------
+#
+class Generator_2(nn.Module):
+
+    def __init__(self, latent_dim=None, data_shape=None):
+        super().__init__()
+        self.latent_dim = latent_dim
+        self.img_shape  = data_shape
+        print('init generator 2         : ',latent_dim,' to ',data_shape)
+
+        self.model = nn.Sequential(
+            
+            nn.Linear(latent_dim, 7*7*64),
+            nn.Unflatten(1, (64,7,7)),
+            
+            # nn.UpsamplingNearest2d( scale_factor=2 ),
+            nn.UpsamplingBilinear2d( scale_factor=2 ),
+            nn.Conv2d( 64,128, (3,3), stride=(1,1), padding=(1,1) ),
+            nn.ReLU(),
+            nn.BatchNorm2d(128),
+
+            # nn.UpsamplingNearest2d( scale_factor=2 ),
+            nn.UpsamplingBilinear2d( scale_factor=2 ),
+            nn.Conv2d( 128,256, (3,3), stride=(1,1), padding=(1,1)),
+            nn.ReLU(),
+            nn.BatchNorm2d(256),
+
+            nn.Conv2d( 256,1, (5,5), stride=(1,1), padding=(2,2)),
+            nn.Sigmoid()
+
+        )
+
+    def forward(self, z):
+        img_nchw = self.model(z)
+        img_nhwc = img_nchw.permute(0, 2, 3, 1) # reformat from NCHW to NHWC
+        # img = img.view(img.size(0), *self.img_shape) # reformat from NCHW to NHWC
+        return img_nhwc
+
+
+

DCGAN.Lightning/modules/QuickDrawDataModule.py

+
+# ------------------------------------------------------------------
+#     _____ _     _ _
+#    |  ___(_) __| | | ___
+#    | |_  | |/ _` | |/ _ \
+#    |  _| | | (_| | |  __/
+#    |_|   |_|\__,_|_|\___|                GAN / QuickDrawDataModule
+# ------------------------------------------------------------------
+# Formation Introduction au Deep Learning  (FIDLE)
+# CNRS/MIAI - https://fidle.cnrs.fr
+# ------------------------------------------------------------------
+# JL Parouty (Mars 2024)
+
+
+
+import numpy as np
+import torch
+from lightning import LightningDataModule
+from torch.utils.data import DataLoader
+
+
+class QuickDrawDataModule(LightningDataModule):
+
+
+    def __init__( self, dataset_file='./sheep.npy', scale=1., batch_size=64, num_workers=4 ):
+
+        super().__init__()
+
+        print('\n---- QuickDrawDataModule initialization ----------------------------')
+        print(f'with : scale={scale}  batch size={batch_size}')
+        
+        self.scale        = scale
+        self.dataset_file = dataset_file
+        self.batch_size   = batch_size
+        self.num_workers  = num_workers
+
+        self.dims         = (28, 28, 1)
+        self.num_classes  = 10
+
+
+
+    def prepare_data(self):
+        pass
+
+
+    def setup(self, stage=None):
+        print('\nDataModule Setup :')
+        # Load dataset
+        # Called at the beginning of each stage (train,val,test)
+        # Here, whatever the stage value, we'll have only one set.
+        data = np.load(self.dataset_file)
+        print('Original dataset shape : ',data.shape)
+
+        # Rescale
+        n=int(self.scale*len(data))
+        data = data[:n]
+        print('Rescaled dataset shape : ',data.shape)
+
+        # Normalize, reshape and shuffle
+        data = data/255
+        data = data.reshape(-1,28,28,1)
+        data = torch.from_numpy(data).float()
+        print('Final dataset shape    : ',data.shape)
+
+        print('Dataset loaded and ready.')
+        self.data_train = data
+
+
+    def train_dataloader(self):
+        # Note : Numpy ndarray is Dataset compliant
+        # Have map-style interface. See https://pytorch.org/docs/stable/data.html 
+        return DataLoader( self.data_train, batch_size=self.batch_size, num_workers=self.num_workers )
\ No newline at end of file

DDPM.PyTorch/requirements.txt

+python==3.10
+jupyterlab
+pytorch 
+torchvision
+tqdm
+matplotlib
+einops
+datasets
\ No newline at end of file

VAE/batch-oar.sh → GTSRB.Keras3/batch_oar.sh

 #!/bin/bash
-#OAR -n VAE with CelebA
+#OAR -n Full convolutions
 #OAR -t gpu
 #OAR -l /nodes=1/gpudevice=1,walltime=01:00:00
-#OAR --stdout _batch/VAE_CelebA_%jobid%.out
-#OAR --stderr _batch/VAE_CelebA_%jobid%.err
+#OAR --stdout full_convolutions_%jobid%.out
+#OAR --stderr full_convolutions_%jobid%.err
 #OAR --project fidle
 
-#---- For cpu
-# use :
-# OAR -l /nodes=1/core=32,walltime=01:00:00
+#---- Note for cpu, set :
+# OAR -l /nodes=1/core=32,walltime=02:00:00
 # and add a 2>/dev/null to ipython xxx
 
 # -----------------------------------------------
@@ -17,20 +16,45 @@
 #        | '_ \ / _` | __/ __| '_ \
 #        | |_) | (_| | || (__| | | |
 #        |_.__/ \__,_|\__\___|_| |_|
-#                       VAE CelebA at GRICAD
+#                             Fidle at GRICAD
 # -----------------------------------------------
 #
+# <!-- TITLE --> [K3GTSRB10] - OAR batch script submission
+# <!-- DESC -->  Bash script for an OAR batch submission of an ipython code
+# <!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->
 
-CONDA_ENV=deeplearning2
-RUN_DIR=~/fidle/VAE
-RUN_IPYNB=05.1-Batch-01.ipynb
+# ==== Notebook parameters =========================================
+
+CONDA_ENV='fidle'
+NOTEBOOK_DIR="~/fidle/GTSRB"
+
+SCRIPT_IPY="03-Better-convolutions.py"
+
+# ---- Environment vars used to override notebook/script parameters
+
+# 'enhanced_dir', 'model_name', 'dataset_name', 'batch_size', 'epochs', 'scale', 'fit_verbosity'
+
+export FIDLE_OVERRIDE_GTSRB3_run_dir="./data"
+export FIDLE_OVERRIDE_GTSRB3_enhanced_dir="./run/GTSRB3"
+export FIDLE_OVERRIDE_GTSRB3_model_name="model_01"
+export FIDLE_OVERRIDE_GTSRB3_dataset_name="set-24x24-L"
+export FIDLE_OVERRIDE_GTSRB3_batch_size=64
+export FIDLE_OVERRIDE_GTSRB3_epochs=5
+export FIDLE_OVERRIDE_GTSRB3_scale=1
+export FIDLE_OVERRIDE_GTSRB3_fit_verbosity=0
+
+# ==================================================================
 
-# ---- Cuda Conda initialization
-#
 echo '------------------------------------------------------------'
 echo "Start : $0"
 echo '------------------------------------------------------------'
-#
+echo "Notebook dir  : $NOTEBOOK_DIR"
+echo "Script        : $SCRIPT_IPY"
+echo "Environment   : $CONDA_ENV"
+echo '------------------------------------------------------------'
+env | grep FIDLE_OVERRIDE | awk 'BEGIN { FS = "=" } ; { printf("%-35s : %s\n",$1,$2) }'
+echo '------------------------------------------------------------'
+
 source /applis/environments/cuda_env.sh dahu 10.0
 source /applis/environments/conda.sh
 #
@@ -38,6 +62,8 @@ conda activate "$CONDA_ENV"
 
 # ---- Run it...
 #
-cd $RUN_DIR
+cd $NOTEBOOK_DIR
+
+ipython "$SCRIPT_IPY"
 
-jupyter nbconvert --to notebook --execute "$RUN_IPYNB"
+echo 'Done.'