Practice Object Recognition Challenge | DPhi

Problem Discussion
#17

Thanks Phil, It worked.

#18

glad it work :sunglasses:

#19

I get length mismatch error while downloading the predicted values. Anyone help to rid the error

#20

Hi @rabinghimire
Please share the screen shot.

#21

I am getting this error while saving the prediction file
ValueError: Length mismatch: Expected axis has 10 elements, new values have 1 elements

Any pointers appreciated

#22

I am also getting the same error. Please help.

#23

I am able to generate the csv file with index, how to post the predictions with commas in the submit file automatically?

#24

When I submit using my predictions, I see my submissions on the problem page, but we also have the submission box on the main platform, right? Do we need to submit anything there too, or not?

#25

Hi @deepchatterjee
Please go through how to submit section of the problem page.
Thanks

#26

Yes, your solution notebook.

#27

Hi @lydianewton
According to this error, you are assigning only 1 element to an object that is expecting 10 elements. Can you share a screenshot of what you’re doing that results in this error?

#28

Hello everyone,
I cannot get more than 60 % percent accuracy in the training dataset ,can anyone suggest some tips to get higher accuracy.
i am using this architecture.
model = Sequential()
model.add(Dense(256, activation=‘relu’, input_shape= (3072,) ))
model.add(Dense(512,input_shape=(256,),activation=‘relu’))###using regularizer
model.add(Dense(512,input_shape=(512,),activation=‘relu’)) ###using regularizer
model.add(Dense(512,input_shape=(512,),activation=‘relu’))
model.add(Dense(512,input_shape=(512,),activation=‘relu’))
model.add(Dense(256,input_shape=(512,),activation=‘relu’))
model.add(Dense(128,input_shape=(256,),activation=‘relu’))
model.add(Dense(10, activation=‘softmax’))
model.compile(loss=‘categorical_crossentropy’, optimizer=‘adam’, metrics=[‘accuracy’])
thanks in advance.

update:
I increased the number of epochs and I am able to get upto 80% accuracy

#29 
test_data = pd.read_csv("https://raw.githubusercontent.com/dphi-official/Datasets/master/cifar_image_flattened_pixels.csv")
not able to come up with the method to bring predictor variable. can someone help?
#30

@goel.amit2008
For this test_data you have to predict the predictor variable using the model you have built.

#31

if someone missed the assignment 1 deadline,is he still eligible for the bootcamp Certificate ?

#32

@manish_kc_06 can we still submit the predictions for this problem ??

#33

Sorry for the delay in the submission closure. You cannot make submissions now.

#34

am i still eligible for completion of camp ?

#35

you can check here if you are eligible or not

Now you cannot submit assignment 1.

#36

thanks for the reply !
looks like i missed my chance .
Anyway will still complete the course.