# Transfer\_learning\_with\_MobileNet\_v1 Assignment 2 of week 2Exercise 3.3 **URL:** \ **Category:** Convolutional Neural Networks\ **Tags:** coursera-platform\ **Created:** [July 21, 2021, 12:05pm UTC](https://community.deeplearning.ai/t/transfer-learning-with-mobilenet-v1-assignment-2-of-week-2exercise-3-3/22422 "2021-07-21T12:05:20Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![Akash02](https://avatars.discourse-cdn.com/v4/letter/a/ba9def/32.png) [@Akash02](https://community.deeplearning.ai/u/Akash02)\ **Post date:** [July 21, 2021, 12:05pm UTC](https://community.deeplearning.ai/t/transfer-learning-with-mobilenet-v1-assignment-2-of-week-2exercise-3-3/22422/1 "2021-07-21T12:05:20Z")
I don’t know where its going wrong .. Any help is appreciated the error states:- ----\> 1 assert type(loss\_function) == tf.python.keras.losses.BinaryCrossentropy, “Not the correct layer” 2 assert loss\_function.from\_logits, “Use from\_logits=True” 3 assert type(optimizer) == tf.keras.optimizers.Adam, “This is not an Adam optimizer” 4 assert optimizer.lr == base\_learning\_rate / 10, “Wrong learning rate” 5 assert metrics[0] == ‘accuracy’, “Wrong metric” AssertionError: Not the correct layer this is my code: for layer in base\_model.layers[:fine\_tune\_at]: layer.trainable = False # Define a BinaryCrossentropy loss function. Use from\_logits=True loss\_function=True # Define an Adam optimizer with a learning rate of 0.1 \* base\_learning\_rate optimizer = tf.keras.optimizers.Adam(learning\_rate=0.1 \* base\_learning\_rate) # Use accuracy as evaluation metric metrics=‘accuracy’ ---
**Author:** ![srikanthreddy21](https://avatars.discourse-cdn.com/v4/letter/s/9dc877/32.png) [@srikanthreddy21](https://community.deeplearning.ai/u/srikanthreddy21)\ **Post date:** [July 22, 2021, 1:42am UTC](https://community.deeplearning.ai/t/transfer-learning-with-mobilenet-v1-assignment-2-of-week-2exercise-3-3/22422/2 "2021-07-22T01:42:29Z")
for defining BinaryCrossEntropyLoss we have to use function from tf.keras as below loss\_function=tf.keras.losses.BinaryCrossentropy(from\_logits=True) Optimizer is correct in your code. Accuracy should be in a list as below. metrics=[‘accuracy’]