added new model, with different hyperparameter from dd3d git

DeepDrug.ipynb

   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
     "from keras.layers import Dense, Flatten, TimeDistributed, Dropout\n",
     "from keras import Input, Model\n",
     "from keras.layers import add, Activation\n",
+    "from keras.layers.advanced_activations import LeakyReLU\n",
     "#from keras.utils import plot_model  # Needs pydot.\n",
-    "from keras.layers import Conv3D, MaxPooling3D"
+    "from keras.layers import Convolution3D, MaxPooling3D"
    ]
   },
   {
     "    return model"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def model_new(): # créer un objet modèle\n",
+    "    \"\"\"\n",
+    "    Return a simple sequentiel model\n",
+    "    \n",
+    "    Returns :\n",
+    "        - model : keras.Model\n",
+    "    \"\"\"\n",
+    "    inputs = Input(shape=(14,32,32,32))\n",
+    "    conv_1 = Convolution3D(filters=64, kernel_size=5, padding=\"valid\", data_format='channels_first')(inputs)\n",
+    "    activation_1 = LeakyReLU(alpha = 0.1)(conv_1)\n",
+    "    drop_1 = Dropout(0.2)(activation_1)\n",
+    "    conv_2 = Convolution3D(filters=64, kernel_size=3, padding=\"valid\", data_format='channels_first')(drop_1)\n",
+    "    activation_2 = LeakyReLU(alpha = 0.1)(conv_2)\n",
+    "    maxpool = MaxPooling3D(pool_size=(2,2,2),\n",
+    "                            strides=None,\n",
+    "                            padding='valid',\n",
+    "                            data_format='channels_first')(activation_2)\n",
+    "    drop_2 = Dropout(0.4)(maxpool)\n",
+    "    flatters = Flatten()(drop_2)\n",
+    "    dense = Dense(128)(flatters)\n",
+    "    activation_3 = LeakyReLU(alpha = 0.1)(dense)\n",
+    "    drop_3 = Dropout(0.4)(activation_3)\n",
+    "    output = Dense(3, activation='softmax')(drop_3)\n",
+    "    model = Model(inputs=inputs, outputs=output)\n",
+    "    my_opt = optimizers.Adam(learning_rate=0.000001, beta_1=0.9, beta_2=0.999, amsgrad=False)\n",
+    "    print(model.summary)\n",
+    "    model.compile(optimizer=my_opt, loss=\"categorical_crossentropy\",\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "    return model"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "my_model = model_light()"
+    "my_model = model_new()"
    ]
   },
   {
    "outputs": [],
    "source": [
     "history_mild_2mp = mild_model.fit(X_train, Y_train, validation_data=(X_test, Y_test), epochs=30, batch_size=32)\n",
-    "my_model.save('light_model_2mp_e30_b32.h5')"
+    "my_model.save('new_model_e30_b32_t1000.h5')"
    ]
   },
   {

DeepDrug.py

 
 # ## Importing library
 
-# In[ ]:
+# In[6]:
 
 
 import numpy as np
 from keras.layers import Dense, Flatten, TimeDistributed, Dropout
 from keras import Input, Model
 from keras.layers import add, Activation
+from keras.layers.advanced_activations import LeakyReLU
 #from keras.utils import plot_model  # Needs pydot.
-from keras.layers import Conv3D, MaxPooling3D
+from keras.layers import Convolution3D, MaxPooling3D
 
 
 # ### used to store model prediction in order to plot roc curve
     return model
 
 
+# In[8]:
+
+
+def model_new(): # créer un objet modèle
+    """
+    Return a simple sequentiel model
+    
+    Returns :
+        - model : keras.Model
+    """
+    inputs = Input(shape=(14,32,32,32))
+    conv_1 = Convolution3D(filters=64, kernel_size=5, padding="valid", data_format='channels_first')(inputs)
+    activation_1 = LeakyReLU(alpha = 0.1)(conv_1)
+    drop_1 = Dropout(0.2)(activation_1)
+    conv_2 = Convolution3D(filters=64, kernel_size=3, padding="valid", data_format='channels_first')(drop_1)
+    activation_2 = LeakyReLU(alpha = 0.1)(conv_2)
+    maxpool = MaxPooling3D(pool_size=(2,2,2),
+                            strides=None,
+                            padding='valid',
+                            data_format='channels_first')(activation_2)
+    drop_2 = Dropout(0.4)(maxpool)
+    flatters = Flatten()(drop_2)
+    dense = Dense(128)(flatters)
+    activation_3 = LeakyReLU(alpha = 0.1)(dense)
+    drop_3 = Dropout(0.4)(activation_3)
+    output = Dense(3, activation='softmax')(drop_3)
+    model = Model(inputs=inputs, outputs=output)
+    my_opt = optimizers.Adam(learning_rate=0.000001, beta_1=0.9, beta_2=0.999, amsgrad=False)
+    print(model.summary)
+    model.compile(optimizer=my_opt, loss="categorical_crossentropy",
+                  metrics=["accuracy"])
+    return model
+
+
 # In[ ]:
 
 
 # In[ ]:
 
 
-my_model = model_light()
+my_model = model_new()
 
 
 # In[ ]:
 # In[ ]:
 
 
-history_mild_2mp = my_model.fit(X_train, Y_train, validation_data=(X_test, Y_test), epochs=30, batch_size=32)
-my_model.save('light_model_2mp_e30_b32.h5')
+history_mild_2mp = mild_model.fit(X_train, Y_train, validation_data=(X_test, Y_test), epochs=30, batch_size=32)
+my_model.save('new_model_e30_b32_t1000.h5')
 
 
 # In[ ]: