Add sliders

app.py

@@ -4,6 +4,7 @@ import numpy as np
 from keras.models import Model
 from keras.saving import load_model
 from keras.layers import *
+from keras.optimizers import RMSProp
 from keras.preprocessing.text import Tokenizer
 import os
 import hashlib
@@ -18,7 +19,7 @@ maxshift = 4
 def hash_str(data: str):
     return hashlib.md5(data.encode('utf-8')).hexdigest()
 
-def train(message: str, data: str):
+def train(message: str, epochs: int, learning_rate: float, emb_size: int, inp_len: int, data: str):
     if "→" not in data or "\n" not in data:
         return "Dataset example:\nquestion→answer\nquestion→answer\netc."
     dset, responses = todset(data)
@@ -66,7 +67,7 @@ def train(message: str, data: str):
         X = np.array(X)
         y = np.array(y)
         
-        model.compile(loss="sparse_categorical_crossentropy", metrics=["accuracy",])
+        model.compile(optimizer=RMSProp(learning_rate=learning_rate), loss="sparse_categorical_crossentropy", metrics=["accuracy",])
         
         model.fit(X, y, epochs=16, batch_size=8, workers=4, use_multiprocessing=True)
         model.save(f"cache/{data_hash}")
@@ -75,5 +76,11 @@ def train(message: str, data: str):
     keras.backend.clear_session()
     return responses[np.argmax(prediction)]
 
-iface = gr.Interface(fn=train, inputs=["text", "text"], outputs="text")
+iface = gr.Interface(fn=train, inputs=["text",
+                                       gr.inputs.Slider(1, 64, 32, step=1, label="Epochs"),
+                                       gr.inputs.Slider(0.00000001, 0.1, 0.001, step=0.00000001, label="Learning rate"),
+                                       gr.inputs.Slider(1, 256, 100, step=1, label="Embedding size"),
+                                       gr.inputs.Slider(1,128, step=1, label="Input Length"),
+                                       "text"],
+                     outputs="text")
 iface.launch()