From 4d19f3b7d461fe0f63e7ccff936909b0ce0c6126 Mon Sep 17 00:00:00 2001
From: Melan <alexleander91@gmail.com>
Date: Fri, 14 Oct 2022 22:45:26 +0200
Subject: Raise an assertion error if no training images have been found.

---
 modules/textual_inversion/dataset.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'modules/textual_inversion/dataset.py')

diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index 67e90afe..12e2f43b 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -81,7 +81,8 @@ class PersonalizedBase(Dataset):
                 entry.cond = cond_model([entry.cond_text]).to(devices.cpu)
 
             self.dataset.append(entry)
-
+        
+        assert len(self.dataset) > 1, "No images have been found in the dataset."
         self.length = len(self.dataset) * repeats
 
         self.initial_indexes = np.arange(self.length) % len(self.dataset)
-- 
cgit v1.2.1


From c7a86f7fe9c0b8967a87e8d709f507d2f44400d8 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Sat, 15 Oct 2022 09:24:59 +0300
Subject: add option to use batch size for training

---
 modules/textual_inversion/dataset.py | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

(limited to 'modules/textual_inversion/dataset.py')

diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index 67e90afe..bd99c0cb 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -24,11 +24,12 @@ class DatasetEntry:
 
 
 class PersonalizedBase(Dataset):
-    def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None, include_cond=False):
-        re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex)>0 else None
+    def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None, include_cond=False, batch_size=1):
+        re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None
 
         self.placeholder_token = placeholder_token
 
+        self.batch_size = batch_size
         self.width = width
         self.height = height
         self.flip = transforms.RandomHorizontalFlip(p=flip_p)
@@ -78,13 +79,13 @@ class PersonalizedBase(Dataset):
 
             if include_cond:
                 entry.cond_text = self.create_text(filename_text)
-                entry.cond = cond_model([entry.cond_text]).to(devices.cpu)
+                entry.cond = cond_model([entry.cond_text]).to(devices.cpu).squeeze(0)
 
             self.dataset.append(entry)
 
-        self.length = len(self.dataset) * repeats
+        self.length = len(self.dataset) * repeats // batch_size
 
-        self.initial_indexes = np.arange(self.length) % len(self.dataset)
+        self.initial_indexes = np.arange(len(self.dataset))
         self.indexes = None
         self.shuffle()
 
@@ -101,13 +102,19 @@ class PersonalizedBase(Dataset):
         return self.length
 
     def __getitem__(self, i):
-        if i % len(self.dataset) == 0:
-            self.shuffle()
+        res = []
 
-        index = self.indexes[i % len(self.indexes)]
-        entry = self.dataset[index]
+        for j in range(self.batch_size):
+            position = i * self.batch_size + j
+            if position % len(self.indexes) == 0:
+                self.shuffle()
 
-        if entry.cond is None:
-            entry.cond_text = self.create_text(entry.filename_text)
+            index = self.indexes[position % len(self.indexes)]
+            entry = self.dataset[index]
 
-        return entry
+            if entry.cond is None:
+                entry.cond_text = self.create_text(entry.filename_text)
+
+            res.append(entry)
+
+        return res
-- 
cgit v1.2.1