diff --git a/docs/graph/predictor.html b/docs/graph/predictor.html
index 5fd570e4f..5d876ff94 100644
--- a/docs/graph/predictor.html
+++ b/docs/graph/predictor.html
@@ -52,10 +52,12 @@ <h1 class="title">Module <code>ktrain.graph.predictor</code></h1>
     def get_classes(self):
         return self.c
 
-    def predict(self, node_ids, return_proba=False):
-        return self.predict_transductive(node_ids, return_proba=return_proba)
+    def predict(self, node_ids, return_proba=False, verbose=0):
+        return self.predict_transductive(
+            node_ids, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_transductive(self, node_ids, return_proba=False):
+    def predict_transductive(self, node_ids, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Performs transductive inference.
@@ -66,11 +68,11 @@ <h1 class="title">Module <code>ktrain.graph.predictor</code></h1>
         gen.batch_size = self.batch_size
         # *_generator methods are deprecated from TF 2.1.0
         # preds = self.model.predict_generator(gen)
-        preds = self.model.predict(gen)
+        preds = self.model.predict(gen, verbose=verbose)
         result = preds if return_proba else [self.c[np.argmax(pred)] for pred in preds]
         return result
 
-    def predict_inductive(self, df, G, return_proba=False):
+    def predict_inductive(self, df, G, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Performs inductive inference.
@@ -82,7 +84,7 @@ <h1 class="title">Module <code>ktrain.graph.predictor</code></h1>
         gen.batch_size = self.batch_size
         # *_generator methods are deprecated from TF 2.1.0
         # preds = self.model.predict_generator(gen)
-        preds = self.model.predict(gen)
+        preds = self.model.predict(gen, verbose=verbose)
         result = preds if return_proba else [self.c[np.argmax(pred)] for pred in preds]
         return result
 
@@ -107,7 +109,7 @@ <h1 class="title">Module <code>ktrain.graph.predictor</code></h1>
     def get_classes(self):
         return self.c
 
-    def predict(self, G, edge_ids, return_proba=False):
+    def predict(self, G, edge_ids, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Performs link prediction
@@ -118,7 +120,7 @@ <h1 class="title">Module <code>ktrain.graph.predictor</code></h1>
         gen.batch_size = self.batch_size
         # *_generator methods are deprecated from TF 2.1.0
         # preds = self.model.predict_generator(gen)
-        preds = self.model.predict(gen)
+        preds = self.model.predict(gen, verbose=verbose)
         preds = np.squeeze(preds)
         if return_proba:
             return [[1 - pred, pred] for pred in preds]
@@ -166,7 +168,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
     def get_classes(self):
         return self.c
 
-    def predict(self, G, edge_ids, return_proba=False):
+    def predict(self, G, edge_ids, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Performs link prediction
@@ -177,7 +179,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         gen.batch_size = self.batch_size
         # *_generator methods are deprecated from TF 2.1.0
         # preds = self.model.predict_generator(gen)
-        preds = self.model.predict(gen)
+        preds = self.model.predict(gen, verbose=verbose)
         preds = np.squeeze(preds)
         if return_proba:
             return [[1 - pred, pred] for pred in preds]
@@ -205,7 +207,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.graph.predictor.LinkPredictor.predict"><code class="name flex">
-<span>def <span class="ident">predict</span></span>(<span>self, G, edge_ids, return_proba=False)</span>
+<span>def <span class="ident">predict</span></span>(<span>self, G, edge_ids, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Performs link prediction
@@ -215,7 +217,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict(self, G, edge_ids, return_proba=False):
+<pre><code class="python">def predict(self, G, edge_ids, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Performs link prediction
@@ -226,7 +228,7 @@ <h3>Methods</h3>
     gen.batch_size = self.batch_size
     # *_generator methods are deprecated from TF 2.1.0
     # preds = self.model.predict_generator(gen)
-    preds = self.model.predict(gen)
+    preds = self.model.predict(gen, verbose=verbose)
     preds = np.squeeze(preds)
     if return_proba:
         return [[1 - pred, pred] for pred in preds]
@@ -278,10 +280,12 @@ <h3>Inherited members</h3>
     def get_classes(self):
         return self.c
 
-    def predict(self, node_ids, return_proba=False):
-        return self.predict_transductive(node_ids, return_proba=return_proba)
+    def predict(self, node_ids, return_proba=False, verbose=0):
+        return self.predict_transductive(
+            node_ids, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_transductive(self, node_ids, return_proba=False):
+    def predict_transductive(self, node_ids, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Performs transductive inference.
@@ -292,11 +296,11 @@ <h3>Inherited members</h3>
         gen.batch_size = self.batch_size
         # *_generator methods are deprecated from TF 2.1.0
         # preds = self.model.predict_generator(gen)
-        preds = self.model.predict(gen)
+        preds = self.model.predict(gen, verbose=verbose)
         result = preds if return_proba else [self.c[np.argmax(pred)] for pred in preds]
         return result
 
-    def predict_inductive(self, df, G, return_proba=False):
+    def predict_inductive(self, df, G, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Performs inductive inference.
@@ -308,7 +312,7 @@ <h3>Inherited members</h3>
         gen.batch_size = self.batch_size
         # *_generator methods are deprecated from TF 2.1.0
         # preds = self.model.predict_generator(gen)
-        preds = self.model.predict(gen)
+        preds = self.model.predict(gen, verbose=verbose)
         result = preds if return_proba else [self.c[np.argmax(pred)] for pred in preds]
         return result</code></pre>
 </details>
@@ -333,7 +337,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.graph.predictor.NodePredictor.predict"><code class="name flex">
-<span>def <span class="ident">predict</span></span>(<span>self, node_ids, return_proba=False)</span>
+<span>def <span class="ident">predict</span></span>(<span>self, node_ids, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -341,12 +345,14 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict(self, node_ids, return_proba=False):
-    return self.predict_transductive(node_ids, return_proba=return_proba)</code></pre>
+<pre><code class="python">def predict(self, node_ids, return_proba=False, verbose=0):
+    return self.predict_transductive(
+        node_ids, return_proba=return_proba, verbose=verbose
+    )</code></pre>
 </details>
 </dd>
 <dt id="ktrain.graph.predictor.NodePredictor.predict_inductive"><code class="name flex">
-<span>def <span class="ident">predict_inductive</span></span>(<span>self, df, G, return_proba=False)</span>
+<span>def <span class="ident">predict_inductive</span></span>(<span>self, df, G, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Performs inductive inference.
@@ -356,7 +362,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_inductive(self, df, G, return_proba=False):
+<pre><code class="python">def predict_inductive(self, df, G, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Performs inductive inference.
@@ -368,13 +374,13 @@ <h3>Methods</h3>
     gen.batch_size = self.batch_size
     # *_generator methods are deprecated from TF 2.1.0
     # preds = self.model.predict_generator(gen)
-    preds = self.model.predict(gen)
+    preds = self.model.predict(gen, verbose=verbose)
     result = preds if return_proba else [self.c[np.argmax(pred)] for pred in preds]
     return result</code></pre>
 </details>
 </dd>
 <dt id="ktrain.graph.predictor.NodePredictor.predict_transductive"><code class="name flex">
-<span>def <span class="ident">predict_transductive</span></span>(<span>self, node_ids, return_proba=False)</span>
+<span>def <span class="ident">predict_transductive</span></span>(<span>self, node_ids, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Performs transductive inference.
@@ -384,7 +390,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_transductive(self, node_ids, return_proba=False):
+<pre><code class="python">def predict_transductive(self, node_ids, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Performs transductive inference.
@@ -395,7 +401,7 @@ <h3>Methods</h3>
     gen.batch_size = self.batch_size
     # *_generator methods are deprecated from TF 2.1.0
     # preds = self.model.predict_generator(gen)
-    preds = self.model.predict(gen)
+    preds = self.model.predict(gen, verbose=verbose)
     result = preds if return_proba else [self.c[np.argmax(pred)] for pred in preds]
     return result</code></pre>
 </details>
diff --git a/docs/tabular/predictor.html b/docs/tabular/predictor.html
index 26563a0a2..ea3020959 100644
--- a/docs/tabular/predictor.html
+++ b/docs/tabular/predictor.html
@@ -55,13 +55,14 @@ <h1 class="title">Module <code>ktrain.tabular.predictor</code></h1>
     def get_classes(self):
         return self.c
 
-    def predict(self, df, return_proba=False):
+    def predict(self, df, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Makes predictions for a test dataframe
         Args:
           df(pd.DataFrame):  a pandas DataFrame in same format as DataFrame used for training model
           return_proba(bool): If True, return probabilities instead of predicted class labels
+          verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
         ```
         &#34;&#34;&#34;
         if not isinstance(df, pd.DataFrame):
@@ -73,7 +74,7 @@ <h1 class="title">Module <code>ktrain.tabular.predictor</code></h1>
         # get predictions
         tseq = self.preproc.preprocess_test(df, verbose=0)
         tseq.batch_size = self.batch_size
-        preds = self.model.predict(tseq)
+        preds = self.model.predict(tseq, verbose=verbose)
         result = (
             preds
             if return_proba or multilabel or not self.c
@@ -248,13 +249,14 @@ <h2 class="section-title" id="header-classes">Classes</h2>
     def get_classes(self):
         return self.c
 
-    def predict(self, df, return_proba=False):
+    def predict(self, df, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Makes predictions for a test dataframe
         Args:
           df(pd.DataFrame):  a pandas DataFrame in same format as DataFrame used for training model
           return_proba(bool): If True, return probabilities instead of predicted class labels
+          verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
         ```
         &#34;&#34;&#34;
         if not isinstance(df, pd.DataFrame):
@@ -266,7 +268,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         # get predictions
         tseq = self.preproc.preprocess_test(df, verbose=0)
         tseq.batch_size = self.batch_size
-        preds = self.model.predict(tseq)
+        preds = self.model.predict(tseq, verbose=verbose)
         result = (
             preds
             if return_proba or multilabel or not self.c
@@ -554,25 +556,27 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.tabular.predictor.TabularPredictor.predict"><code class="name flex">
-<span>def <span class="ident">predict</span></span>(<span>self, df, return_proba=False)</span>
+<span>def <span class="ident">predict</span></span>(<span>self, df, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Makes predictions for a test dataframe
 Args:
   df(pd.DataFrame):  a pandas DataFrame in same format as DataFrame used for training model
   return_proba(bool): If True, return probabilities instead of predicted class labels
+  verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
 </code></pre></div>
 <details class="source">
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict(self, df, return_proba=False):
+<pre><code class="python">def predict(self, df, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Makes predictions for a test dataframe
     Args:
       df(pd.DataFrame):  a pandas DataFrame in same format as DataFrame used for training model
       return_proba(bool): If True, return probabilities instead of predicted class labels
+      verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
     ```
     &#34;&#34;&#34;
     if not isinstance(df, pd.DataFrame):
@@ -584,7 +588,7 @@ <h3>Methods</h3>
     # get predictions
     tseq = self.preproc.preprocess_test(df, verbose=0)
     tseq.batch_size = self.batch_size
-    preds = self.model.predict(tseq)
+    preds = self.model.predict(tseq, verbose=verbose)
     result = (
         preds
         if return_proba or multilabel or not self.c
diff --git a/docs/text/ner/anago/preprocessing.html b/docs/text/ner/anago/preprocessing.html
index 2421bc26b..7a3b96605 100644
--- a/docs/text/ner/anago/preprocessing.html
+++ b/docs/text/ner/anago/preprocessing.html
@@ -790,7 +790,6 @@ <h3>Ancestors</h3>
 <ul class="hlist">
 <li>sklearn.base.BaseEstimator</li>
 <li>sklearn.base.TransformerMixin</li>
-<li>sklearn.utils._set_output._SetOutputMixin</li>
 </ul>
 <h3>Static methods</h3>
 <dl>
diff --git a/docs/text/predictor.html b/docs/text/predictor.html
index ab78deb12..d7c4f24bd 100644
--- a/docs/text/predictor.html
+++ b/docs/text/predictor.html
@@ -53,7 +53,7 @@ <h1 class="title">Module <code>ktrain.text.predictor</code></h1>
     def get_classes(self):
         return self.c
 
-    def predict(self, texts, return_proba=False):
+    def predict(self, texts, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
 
@@ -68,6 +68,7 @@ <h1 class="title">Module <code>ktrain.text.predictor</code></h1>
                            A single tuple of the form (str, str) is automatically treated as sentence pair classification, so
                            please refrain from using tuples for text classification tasks.
           return_proba(bool): If True, return probabilities instead of predicted class labels
+          verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
         ```
         &#34;&#34;&#34;
 
@@ -82,7 +83,7 @@ <h1 class="title">Module <code>ktrain.text.predictor</code></h1>
             tseq = self.preproc.preprocess_test(texts, verbose=0)
             tseq.batch_size = self.batch_size
             tfd = tseq.to_tfdataset(train=False)
-            preds = self.model.predict(tfd)
+            preds = self.model.predict(tfd, verbose=verbose)
             if hasattr(
                 preds, &#34;logits&#34;
             ):  # dep_fix: breaking change - also needed for LongFormer
@@ -95,7 +96,9 @@ <h1 class="title">Module <code>ktrain.text.predictor</code></h1>
                 preds = preds[0]
         else:
             texts = self.preproc.preprocess(texts)
-            preds = self.model.predict(texts, batch_size=self.batch_size)
+            preds = self.model.predict(
+                texts, batch_size=self.batch_size, verbose=verbose
+            )
 
         # process predictions
         if U.is_huggingface(model=self.model):
@@ -120,7 +123,7 @@ <h1 class="title">Module <code>ktrain.text.predictor</code></h1>
         else:
             return result
 
-    def predict_proba(self, texts):
+    def predict_proba(self, texts, verbose=0):
         &#34;&#34;&#34;
         ```
         Makes predictions for a list of strings where each string is a document
@@ -128,7 +131,7 @@ <h1 class="title">Module <code>ktrain.text.predictor</code></h1>
         Returns probabilities of each class.
         ```
         &#34;&#34;&#34;
-        return self.predict(texts, return_proba=True)
+        return self.predict(texts, return_proba=True, verbose=verbose)
 
     def explain(self, doc, truncate_len=512, all_targets=False, n_samples=2500):
         &#34;&#34;&#34;
@@ -230,7 +233,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
     def get_classes(self):
         return self.c
 
-    def predict(self, texts, return_proba=False):
+    def predict(self, texts, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
 
@@ -245,6 +248,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
                            A single tuple of the form (str, str) is automatically treated as sentence pair classification, so
                            please refrain from using tuples for text classification tasks.
           return_proba(bool): If True, return probabilities instead of predicted class labels
+          verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
         ```
         &#34;&#34;&#34;
 
@@ -259,7 +263,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
             tseq = self.preproc.preprocess_test(texts, verbose=0)
             tseq.batch_size = self.batch_size
             tfd = tseq.to_tfdataset(train=False)
-            preds = self.model.predict(tfd)
+            preds = self.model.predict(tfd, verbose=verbose)
             if hasattr(
                 preds, &#34;logits&#34;
             ):  # dep_fix: breaking change - also needed for LongFormer
@@ -272,7 +276,9 @@ <h2 class="section-title" id="header-classes">Classes</h2>
                 preds = preds[0]
         else:
             texts = self.preproc.preprocess(texts)
-            preds = self.model.predict(texts, batch_size=self.batch_size)
+            preds = self.model.predict(
+                texts, batch_size=self.batch_size, verbose=verbose
+            )
 
         # process predictions
         if U.is_huggingface(model=self.model):
@@ -297,7 +303,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         else:
             return result
 
-    def predict_proba(self, texts):
+    def predict_proba(self, texts, verbose=0):
         &#34;&#34;&#34;
         ```
         Makes predictions for a list of strings where each string is a document
@@ -305,7 +311,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         Returns probabilities of each class.
         ```
         &#34;&#34;&#34;
-        return self.predict(texts, return_proba=True)
+        return self.predict(texts, return_proba=True, verbose=verbose)
 
     def explain(self, doc, truncate_len=512, all_targets=False, n_samples=2500):
         &#34;&#34;&#34;
@@ -456,7 +462,7 @@ <h2 id="args">Args</h2>
 </details>
 </dd>
 <dt id="ktrain.text.predictor.TextPredictor.predict"><code class="name flex">
-<span>def <span class="ident">predict</span></span>(<span>self, texts, return_proba=False)</span>
+<span>def <span class="ident">predict</span></span>(<span>self, texts, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>
@@ -471,12 +477,13 @@ <h2 id="args">Args</h2>
                    A single tuple of the form (str, str) is automatically treated as sentence pair classification, so
                    please refrain from using tuples for text classification tasks.
   return_proba(bool): If True, return probabilities instead of predicted class labels
+  verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
 </code></pre></div>
 <details class="source">
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict(self, texts, return_proba=False):
+<pre><code class="python">def predict(self, texts, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
 
@@ -491,6 +498,7 @@ <h2 id="args">Args</h2>
                        A single tuple of the form (str, str) is automatically treated as sentence pair classification, so
                        please refrain from using tuples for text classification tasks.
       return_proba(bool): If True, return probabilities instead of predicted class labels
+      verbose(int): verbosity: 0 (silent), 1 (progress bar), 2 (single line)
     ```
     &#34;&#34;&#34;
 
@@ -505,7 +513,7 @@ <h2 id="args">Args</h2>
         tseq = self.preproc.preprocess_test(texts, verbose=0)
         tseq.batch_size = self.batch_size
         tfd = tseq.to_tfdataset(train=False)
-        preds = self.model.predict(tfd)
+        preds = self.model.predict(tfd, verbose=verbose)
         if hasattr(
             preds, &#34;logits&#34;
         ):  # dep_fix: breaking change - also needed for LongFormer
@@ -518,7 +526,9 @@ <h2 id="args">Args</h2>
             preds = preds[0]
     else:
         texts = self.preproc.preprocess(texts)
-        preds = self.model.predict(texts, batch_size=self.batch_size)
+        preds = self.model.predict(
+            texts, batch_size=self.batch_size, verbose=verbose
+        )
 
     # process predictions
     if U.is_huggingface(model=self.model):
@@ -545,7 +555,7 @@ <h2 id="args">Args</h2>
 </details>
 </dd>
 <dt id="ktrain.text.predictor.TextPredictor.predict_proba"><code class="name flex">
-<span>def <span class="ident">predict_proba</span></span>(<span>self, texts)</span>
+<span>def <span class="ident">predict_proba</span></span>(<span>self, texts, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Makes predictions for a list of strings where each string is a document
@@ -556,7 +566,7 @@ <h2 id="args">Args</h2>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba(self, texts):
+<pre><code class="python">def predict_proba(self, texts, verbose=0):
     &#34;&#34;&#34;
     ```
     Makes predictions for a list of strings where each string is a document
@@ -564,7 +574,7 @@ <h2 id="args">Args</h2>
     Returns probabilities of each class.
     ```
     &#34;&#34;&#34;
-    return self.predict(texts, return_proba=True)</code></pre>
+    return self.predict(texts, return_proba=True, verbose=verbose)</code></pre>
 </details>
 </dd>
 </dl>
diff --git a/docs/version.html b/docs/version.html
index 5d399b19c..df754c88a 100644
--- a/docs/version.html
+++ b/docs/version.html
@@ -27,7 +27,7 @@ <h1 class="title">Module <code>ktrain.version</code></h1>
 <span>Expand source code</span>
 </summary>
 <pre><code class="python">__all__ = [&#34;__version__&#34;]
-__version__ = &#34;0.33.3&#34;</code></pre>
+__version__ = &#34;0.33.4&#34;</code></pre>
 </details>
 </section>
 <section>
diff --git a/docs/vision/index.html b/docs/vision/index.html
index 956b485e9..d6c9cef42 100644
--- a/docs/vision/index.html
+++ b/docs/vision/index.html
@@ -1182,7 +1182,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         x = np.expand_dims(x, axis=0)
         return eli5.show_prediction(self.model, x)
 
-    def predict(self, data, return_proba=False):
+    def predict(self, data, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts class from image in array format.
@@ -1192,9 +1192,11 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         if not isinstance(data, np.ndarray):
             raise ValueError(&#34;data must be numpy.ndarray&#34;)
         (generator, steps) = self.preproc.preprocess(data, batch_size=self.batch_size)
-        return self.predict_generator(generator, steps=steps, return_proba=return_proba)
+        return self.predict_generator(
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_filename(self, img_path, return_proba=False):
+    def predict_filename(self, img_path, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts class from filepath to single image file.
@@ -1206,9 +1208,11 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         (generator, steps) = self.preproc.preprocess(
             img_path, batch_size=self.batch_size
         )
-        return self.predict_generator(generator, steps=steps, return_proba=return_proba)
+        return self.predict_generator(
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_folder(self, folder, return_proba=False):
+    def predict_folder(self, folder, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts the classes of all images in a folder.
@@ -1220,13 +1224,13 @@ <h2 class="section-title" id="header-classes">Classes</h2>
             raise ValueError(&#34;folder must be valid directory&#34;)
         (generator, steps) = self.preproc.preprocess(folder, batch_size=self.batch_size)
         result = self.predict_generator(
-            generator, steps=steps, return_proba=return_proba
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
         )
         if len(result) != len(generator.filenames):
             raise Exception(&#34;number of results does not equal number of filenames&#34;)
         return list(zip(generator.filenames, result))
 
-    def predict_generator(self, generator, steps=None, return_proba=False):
+    def predict_generator(self, generator, steps=None, return_proba=False, verbose=0):
         # loss = self.model.loss
         # if callable(loss): loss = loss.__name__
         # treat_multilabel = False
@@ -1238,7 +1242,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
             return_proba = True
         # *_generator methods are deprecated from TF 2.1.0
         # preds =  self.model.predict_generator(generator, steps=steps)
-        preds = self.model.predict(generator, steps=steps)
+        preds = self.model.predict(generator, steps=steps, verbose=verbose)
         result = (
             preds
             if return_proba or multilabel
@@ -1251,17 +1255,19 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         else:
             return result
 
-    def predict_proba(self, data):
-        return self.predict(data, return_proba=True)
+    def predict_proba(self, data, verbose=0):
+        return self.predict(data, return_proba=True, verbose=verbose)
 
-    def predict_proba_folder(self, folder):
-        return self.predict_folder(folder, return_proba=True)
+    def predict_proba_folder(self, folder, verbose=0):
+        return self.predict_folder(folder, return_proba=True, verbose=verbose)
 
-    def predict_proba_filename(self, img_path):
-        return self.predict_filename(img_path, return_proba=True)
+    def predict_proba_filename(self, img_path, verbose=0):
+        return self.predict_filename(img_path, return_proba=True, verbose=verbose)
 
-    def predict_proba_generator(self, generator, steps=None):
-        return self.predict_proba_generator(generator, steps=steps, return_proba=True)
+    def predict_proba_generator(self, generator, steps=None, verbose=0):
+        return self.predict_proba_generator(
+            generator, steps=steps, return_proba=True, verbose=verbose
+        )
 
     def analyze_valid(self, generator, print_report=True, multilabel=None):
         &#34;&#34;&#34;
@@ -1427,7 +1433,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict"><code class="name flex">
-<span>def <span class="ident">predict</span></span>(<span>self, data, return_proba=False)</span>
+<span>def <span class="ident">predict</span></span>(<span>self, data, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Predicts class from image in array format.
@@ -1437,7 +1443,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict(self, data, return_proba=False):
+<pre><code class="python">def predict(self, data, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Predicts class from image in array format.
@@ -1447,11 +1453,13 @@ <h3>Methods</h3>
     if not isinstance(data, np.ndarray):
         raise ValueError(&#34;data must be numpy.ndarray&#34;)
     (generator, steps) = self.preproc.preprocess(data, batch_size=self.batch_size)
-    return self.predict_generator(generator, steps=steps, return_proba=return_proba)</code></pre>
+    return self.predict_generator(
+        generator, steps=steps, return_proba=return_proba, verbose=verbose
+    )</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict_filename"><code class="name flex">
-<span>def <span class="ident">predict_filename</span></span>(<span>self, img_path, return_proba=False)</span>
+<span>def <span class="ident">predict_filename</span></span>(<span>self, img_path, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Predicts class from filepath to single image file.
@@ -1461,7 +1469,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_filename(self, img_path, return_proba=False):
+<pre><code class="python">def predict_filename(self, img_path, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Predicts class from filepath to single image file.
@@ -1473,11 +1481,13 @@ <h3>Methods</h3>
     (generator, steps) = self.preproc.preprocess(
         img_path, batch_size=self.batch_size
     )
-    return self.predict_generator(generator, steps=steps, return_proba=return_proba)</code></pre>
+    return self.predict_generator(
+        generator, steps=steps, return_proba=return_proba, verbose=verbose
+    )</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict_folder"><code class="name flex">
-<span>def <span class="ident">predict_folder</span></span>(<span>self, folder, return_proba=False)</span>
+<span>def <span class="ident">predict_folder</span></span>(<span>self, folder, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Predicts the classes of all images in a folder.
@@ -1487,7 +1497,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_folder(self, folder, return_proba=False):
+<pre><code class="python">def predict_folder(self, folder, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Predicts the classes of all images in a folder.
@@ -1499,7 +1509,7 @@ <h3>Methods</h3>
         raise ValueError(&#34;folder must be valid directory&#34;)
     (generator, steps) = self.preproc.preprocess(folder, batch_size=self.batch_size)
     result = self.predict_generator(
-        generator, steps=steps, return_proba=return_proba
+        generator, steps=steps, return_proba=return_proba, verbose=verbose
     )
     if len(result) != len(generator.filenames):
         raise Exception(&#34;number of results does not equal number of filenames&#34;)
@@ -1507,7 +1517,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict_generator"><code class="name flex">
-<span>def <span class="ident">predict_generator</span></span>(<span>self, generator, steps=None, return_proba=False)</span>
+<span>def <span class="ident">predict_generator</span></span>(<span>self, generator, steps=None, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -1515,7 +1525,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_generator(self, generator, steps=None, return_proba=False):
+<pre><code class="python">def predict_generator(self, generator, steps=None, return_proba=False, verbose=0):
     # loss = self.model.loss
     # if callable(loss): loss = loss.__name__
     # treat_multilabel = False
@@ -1527,7 +1537,7 @@ <h3>Methods</h3>
         return_proba = True
     # *_generator methods are deprecated from TF 2.1.0
     # preds =  self.model.predict_generator(generator, steps=steps)
-    preds = self.model.predict(generator, steps=steps)
+    preds = self.model.predict(generator, steps=steps, verbose=verbose)
     result = (
         preds
         if return_proba or multilabel
@@ -1542,7 +1552,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict_proba"><code class="name flex">
-<span>def <span class="ident">predict_proba</span></span>(<span>self, data)</span>
+<span>def <span class="ident">predict_proba</span></span>(<span>self, data, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -1550,12 +1560,12 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba(self, data):
-    return self.predict(data, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba(self, data, verbose=0):
+    return self.predict(data, return_proba=True, verbose=verbose)</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict_proba_filename"><code class="name flex">
-<span>def <span class="ident">predict_proba_filename</span></span>(<span>self, img_path)</span>
+<span>def <span class="ident">predict_proba_filename</span></span>(<span>self, img_path, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -1563,12 +1573,12 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba_filename(self, img_path):
-    return self.predict_filename(img_path, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba_filename(self, img_path, verbose=0):
+    return self.predict_filename(img_path, return_proba=True, verbose=verbose)</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict_proba_folder"><code class="name flex">
-<span>def <span class="ident">predict_proba_folder</span></span>(<span>self, folder)</span>
+<span>def <span class="ident">predict_proba_folder</span></span>(<span>self, folder, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -1576,12 +1586,12 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba_folder(self, folder):
-    return self.predict_folder(folder, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba_folder(self, folder, verbose=0):
+    return self.predict_folder(folder, return_proba=True, verbose=verbose)</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.ImagePredictor.predict_proba_generator"><code class="name flex">
-<span>def <span class="ident">predict_proba_generator</span></span>(<span>self, generator, steps=None)</span>
+<span>def <span class="ident">predict_proba_generator</span></span>(<span>self, generator, steps=None, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -1589,8 +1599,10 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba_generator(self, generator, steps=None):
-    return self.predict_proba_generator(generator, steps=steps, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba_generator(self, generator, steps=None, verbose=0):
+    return self.predict_proba_generator(
+        generator, steps=steps, return_proba=True, verbose=verbose
+    )</code></pre>
 </details>
 </dd>
 </dl>
diff --git a/docs/vision/predictor.html b/docs/vision/predictor.html
index c68fad643..81737d9eb 100644
--- a/docs/vision/predictor.html
+++ b/docs/vision/predictor.html
@@ -91,7 +91,7 @@ <h1 class="title">Module <code>ktrain.vision.predictor</code></h1>
         x = np.expand_dims(x, axis=0)
         return eli5.show_prediction(self.model, x)
 
-    def predict(self, data, return_proba=False):
+    def predict(self, data, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts class from image in array format.
@@ -101,9 +101,11 @@ <h1 class="title">Module <code>ktrain.vision.predictor</code></h1>
         if not isinstance(data, np.ndarray):
             raise ValueError(&#34;data must be numpy.ndarray&#34;)
         (generator, steps) = self.preproc.preprocess(data, batch_size=self.batch_size)
-        return self.predict_generator(generator, steps=steps, return_proba=return_proba)
+        return self.predict_generator(
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_filename(self, img_path, return_proba=False):
+    def predict_filename(self, img_path, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts class from filepath to single image file.
@@ -115,9 +117,11 @@ <h1 class="title">Module <code>ktrain.vision.predictor</code></h1>
         (generator, steps) = self.preproc.preprocess(
             img_path, batch_size=self.batch_size
         )
-        return self.predict_generator(generator, steps=steps, return_proba=return_proba)
+        return self.predict_generator(
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_folder(self, folder, return_proba=False):
+    def predict_folder(self, folder, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts the classes of all images in a folder.
@@ -129,13 +133,13 @@ <h1 class="title">Module <code>ktrain.vision.predictor</code></h1>
             raise ValueError(&#34;folder must be valid directory&#34;)
         (generator, steps) = self.preproc.preprocess(folder, batch_size=self.batch_size)
         result = self.predict_generator(
-            generator, steps=steps, return_proba=return_proba
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
         )
         if len(result) != len(generator.filenames):
             raise Exception(&#34;number of results does not equal number of filenames&#34;)
         return list(zip(generator.filenames, result))
 
-    def predict_generator(self, generator, steps=None, return_proba=False):
+    def predict_generator(self, generator, steps=None, return_proba=False, verbose=0):
         # loss = self.model.loss
         # if callable(loss): loss = loss.__name__
         # treat_multilabel = False
@@ -147,7 +151,7 @@ <h1 class="title">Module <code>ktrain.vision.predictor</code></h1>
             return_proba = True
         # *_generator methods are deprecated from TF 2.1.0
         # preds =  self.model.predict_generator(generator, steps=steps)
-        preds = self.model.predict(generator, steps=steps)
+        preds = self.model.predict(generator, steps=steps, verbose=verbose)
         result = (
             preds
             if return_proba or multilabel
@@ -160,17 +164,19 @@ <h1 class="title">Module <code>ktrain.vision.predictor</code></h1>
         else:
             return result
 
-    def predict_proba(self, data):
-        return self.predict(data, return_proba=True)
+    def predict_proba(self, data, verbose=0):
+        return self.predict(data, return_proba=True, verbose=verbose)
 
-    def predict_proba_folder(self, folder):
-        return self.predict_folder(folder, return_proba=True)
+    def predict_proba_folder(self, folder, verbose=0):
+        return self.predict_folder(folder, return_proba=True, verbose=verbose)
 
-    def predict_proba_filename(self, img_path):
-        return self.predict_filename(img_path, return_proba=True)
+    def predict_proba_filename(self, img_path, verbose=0):
+        return self.predict_filename(img_path, return_proba=True, verbose=verbose)
 
-    def predict_proba_generator(self, generator, steps=None):
-        return self.predict_proba_generator(generator, steps=steps, return_proba=True)
+    def predict_proba_generator(self, generator, steps=None, verbose=0):
+        return self.predict_proba_generator(
+            generator, steps=steps, return_proba=True, verbose=verbose
+        )
 
     def analyze_valid(self, generator, print_report=True, multilabel=None):
         &#34;&#34;&#34;
@@ -295,7 +301,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         x = np.expand_dims(x, axis=0)
         return eli5.show_prediction(self.model, x)
 
-    def predict(self, data, return_proba=False):
+    def predict(self, data, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts class from image in array format.
@@ -305,9 +311,11 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         if not isinstance(data, np.ndarray):
             raise ValueError(&#34;data must be numpy.ndarray&#34;)
         (generator, steps) = self.preproc.preprocess(data, batch_size=self.batch_size)
-        return self.predict_generator(generator, steps=steps, return_proba=return_proba)
+        return self.predict_generator(
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_filename(self, img_path, return_proba=False):
+    def predict_filename(self, img_path, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts class from filepath to single image file.
@@ -319,9 +327,11 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         (generator, steps) = self.preproc.preprocess(
             img_path, batch_size=self.batch_size
         )
-        return self.predict_generator(generator, steps=steps, return_proba=return_proba)
+        return self.predict_generator(
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
+        )
 
-    def predict_folder(self, folder, return_proba=False):
+    def predict_folder(self, folder, return_proba=False, verbose=0):
         &#34;&#34;&#34;
         ```
         Predicts the classes of all images in a folder.
@@ -333,13 +343,13 @@ <h2 class="section-title" id="header-classes">Classes</h2>
             raise ValueError(&#34;folder must be valid directory&#34;)
         (generator, steps) = self.preproc.preprocess(folder, batch_size=self.batch_size)
         result = self.predict_generator(
-            generator, steps=steps, return_proba=return_proba
+            generator, steps=steps, return_proba=return_proba, verbose=verbose
         )
         if len(result) != len(generator.filenames):
             raise Exception(&#34;number of results does not equal number of filenames&#34;)
         return list(zip(generator.filenames, result))
 
-    def predict_generator(self, generator, steps=None, return_proba=False):
+    def predict_generator(self, generator, steps=None, return_proba=False, verbose=0):
         # loss = self.model.loss
         # if callable(loss): loss = loss.__name__
         # treat_multilabel = False
@@ -351,7 +361,7 @@ <h2 class="section-title" id="header-classes">Classes</h2>
             return_proba = True
         # *_generator methods are deprecated from TF 2.1.0
         # preds =  self.model.predict_generator(generator, steps=steps)
-        preds = self.model.predict(generator, steps=steps)
+        preds = self.model.predict(generator, steps=steps, verbose=verbose)
         result = (
             preds
             if return_proba or multilabel
@@ -364,17 +374,19 @@ <h2 class="section-title" id="header-classes">Classes</h2>
         else:
             return result
 
-    def predict_proba(self, data):
-        return self.predict(data, return_proba=True)
+    def predict_proba(self, data, verbose=0):
+        return self.predict(data, return_proba=True, verbose=verbose)
 
-    def predict_proba_folder(self, folder):
-        return self.predict_folder(folder, return_proba=True)
+    def predict_proba_folder(self, folder, verbose=0):
+        return self.predict_folder(folder, return_proba=True, verbose=verbose)
 
-    def predict_proba_filename(self, img_path):
-        return self.predict_filename(img_path, return_proba=True)
+    def predict_proba_filename(self, img_path, verbose=0):
+        return self.predict_filename(img_path, return_proba=True, verbose=verbose)
 
-    def predict_proba_generator(self, generator, steps=None):
-        return self.predict_proba_generator(generator, steps=steps, return_proba=True)
+    def predict_proba_generator(self, generator, steps=None, verbose=0):
+        return self.predict_proba_generator(
+            generator, steps=steps, return_proba=True, verbose=verbose
+        )
 
     def analyze_valid(self, generator, print_report=True, multilabel=None):
         &#34;&#34;&#34;
@@ -540,7 +552,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict"><code class="name flex">
-<span>def <span class="ident">predict</span></span>(<span>self, data, return_proba=False)</span>
+<span>def <span class="ident">predict</span></span>(<span>self, data, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Predicts class from image in array format.
@@ -550,7 +562,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict(self, data, return_proba=False):
+<pre><code class="python">def predict(self, data, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Predicts class from image in array format.
@@ -560,11 +572,13 @@ <h3>Methods</h3>
     if not isinstance(data, np.ndarray):
         raise ValueError(&#34;data must be numpy.ndarray&#34;)
     (generator, steps) = self.preproc.preprocess(data, batch_size=self.batch_size)
-    return self.predict_generator(generator, steps=steps, return_proba=return_proba)</code></pre>
+    return self.predict_generator(
+        generator, steps=steps, return_proba=return_proba, verbose=verbose
+    )</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict_filename"><code class="name flex">
-<span>def <span class="ident">predict_filename</span></span>(<span>self, img_path, return_proba=False)</span>
+<span>def <span class="ident">predict_filename</span></span>(<span>self, img_path, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Predicts class from filepath to single image file.
@@ -574,7 +588,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_filename(self, img_path, return_proba=False):
+<pre><code class="python">def predict_filename(self, img_path, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Predicts class from filepath to single image file.
@@ -586,11 +600,13 @@ <h3>Methods</h3>
     (generator, steps) = self.preproc.preprocess(
         img_path, batch_size=self.batch_size
     )
-    return self.predict_generator(generator, steps=steps, return_proba=return_proba)</code></pre>
+    return self.predict_generator(
+        generator, steps=steps, return_proba=return_proba, verbose=verbose
+    )</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict_folder"><code class="name flex">
-<span>def <span class="ident">predict_folder</span></span>(<span>self, folder, return_proba=False)</span>
+<span>def <span class="ident">predict_folder</span></span>(<span>self, folder, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"><pre><code>Predicts the classes of all images in a folder.
@@ -600,7 +616,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_folder(self, folder, return_proba=False):
+<pre><code class="python">def predict_folder(self, folder, return_proba=False, verbose=0):
     &#34;&#34;&#34;
     ```
     Predicts the classes of all images in a folder.
@@ -612,7 +628,7 @@ <h3>Methods</h3>
         raise ValueError(&#34;folder must be valid directory&#34;)
     (generator, steps) = self.preproc.preprocess(folder, batch_size=self.batch_size)
     result = self.predict_generator(
-        generator, steps=steps, return_proba=return_proba
+        generator, steps=steps, return_proba=return_proba, verbose=verbose
     )
     if len(result) != len(generator.filenames):
         raise Exception(&#34;number of results does not equal number of filenames&#34;)
@@ -620,7 +636,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict_generator"><code class="name flex">
-<span>def <span class="ident">predict_generator</span></span>(<span>self, generator, steps=None, return_proba=False)</span>
+<span>def <span class="ident">predict_generator</span></span>(<span>self, generator, steps=None, return_proba=False, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -628,7 +644,7 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_generator(self, generator, steps=None, return_proba=False):
+<pre><code class="python">def predict_generator(self, generator, steps=None, return_proba=False, verbose=0):
     # loss = self.model.loss
     # if callable(loss): loss = loss.__name__
     # treat_multilabel = False
@@ -640,7 +656,7 @@ <h3>Methods</h3>
         return_proba = True
     # *_generator methods are deprecated from TF 2.1.0
     # preds =  self.model.predict_generator(generator, steps=steps)
-    preds = self.model.predict(generator, steps=steps)
+    preds = self.model.predict(generator, steps=steps, verbose=verbose)
     result = (
         preds
         if return_proba or multilabel
@@ -655,7 +671,7 @@ <h3>Methods</h3>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict_proba"><code class="name flex">
-<span>def <span class="ident">predict_proba</span></span>(<span>self, data)</span>
+<span>def <span class="ident">predict_proba</span></span>(<span>self, data, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -663,12 +679,12 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba(self, data):
-    return self.predict(data, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba(self, data, verbose=0):
+    return self.predict(data, return_proba=True, verbose=verbose)</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict_proba_filename"><code class="name flex">
-<span>def <span class="ident">predict_proba_filename</span></span>(<span>self, img_path)</span>
+<span>def <span class="ident">predict_proba_filename</span></span>(<span>self, img_path, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -676,12 +692,12 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba_filename(self, img_path):
-    return self.predict_filename(img_path, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba_filename(self, img_path, verbose=0):
+    return self.predict_filename(img_path, return_proba=True, verbose=verbose)</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict_proba_folder"><code class="name flex">
-<span>def <span class="ident">predict_proba_folder</span></span>(<span>self, folder)</span>
+<span>def <span class="ident">predict_proba_folder</span></span>(<span>self, folder, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -689,12 +705,12 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba_folder(self, folder):
-    return self.predict_folder(folder, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba_folder(self, folder, verbose=0):
+    return self.predict_folder(folder, return_proba=True, verbose=verbose)</code></pre>
 </details>
 </dd>
 <dt id="ktrain.vision.predictor.ImagePredictor.predict_proba_generator"><code class="name flex">
-<span>def <span class="ident">predict_proba_generator</span></span>(<span>self, generator, steps=None)</span>
+<span>def <span class="ident">predict_proba_generator</span></span>(<span>self, generator, steps=None, verbose=0)</span>
 </code></dt>
 <dd>
 <div class="desc"></div>
@@ -702,8 +718,10 @@ <h3>Methods</h3>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">def predict_proba_generator(self, generator, steps=None):
-    return self.predict_proba_generator(generator, steps=steps, return_proba=True)</code></pre>
+<pre><code class="python">def predict_proba_generator(self, generator, steps=None, verbose=0):
+    return self.predict_proba_generator(
+        generator, steps=steps, return_proba=True, verbose=verbose
+    )</code></pre>
 </details>
 </dd>
 </dl>