Hyper Parameters Section Error

Dear All,

After Finishing Building the Model I Moved to (HyperParameters) section but when I enter I got the following error message:

TypeError : can only concatenate tuple (not “dict”) to tuple

Please let me know how to solve this error cuz I’m not able to train the model?

This is the Model how it looks like almost the same with (CIFAR-10 )

Can you show your data tab settings ? Or you can share the model by exporting it from model tab.

Also Creating Wizard for the Model I got the following error:

Here is it

Here is the code:

data:
dataset: {name: train, samples: 22424, type: private}
datasetLoadOption: batch
kfold: 1
mapping:
Image:
options: {}
port: ‘’
shape: ‘’
type: Categorical
Rating:
options: {}
port: ‘’
shape: ‘’
type: Categorical
numPorts: 1
samples: {split: 1, test: 0, training: 17939, validation: 4484}
shuffle: false
model:
connections:

  • {source: Flatten_1, target: Dense_1}
  • {source: Dropout_2, target: Flatten_1}
  • {source: Dense_1, target: Dropout_3}
  • {source: Dropout_3, target: Dense_2}
  • {source: Dense_2, target: Output_1}
  • {source: MaxPooling2D_1, target: Dropout_1}
  • {source: Dropout_1, target: Convolution2D_2}
  • {source: Convolution2D_3, target: MaxPooling2D_2}
  • {source: Input_1, target: BatchNormalization_1}
  • {source: BatchNormalization_1, target: Convolution2D_1}
  • {source: MaxPooling2D_2, target: Dropout_2}
  • {source: Convolution2D_4, target: MaxPooling2D_1}
  • {source: Convolution2D_1, target: Convolution2D_4}
  • {source: Convolution2D_2, target: Convolution2D_3}
    layers:
  • args: {}
    class: Input
    name: Input_1
    x: 10
    y: 50
  • args: {}
    class: Output
    name: Output_1
    x: 824.4
    y: 615.88
  • args: {activation: relu, border_mode: same, nb_col: ‘3’, nb_filter: ‘32’, nb_row: ‘3’}
    class: Convolution2D
    name: Convolution2D_1
    x: 9
    y: 304
  • args: {axis: ‘1’}
    class: BatchNormalization
    name: BatchNormalization_1
    x: 12
    y: 183
  • args: {activation: relu, border_mode: same, nb_col: ‘3’, nb_filter: ‘64’, nb_row: ‘3’}
    class: Convolution2D
    name: Convolution2D_2
    x: 415.24
    y: 54.019999999999996
  • args: {activation: relu, nb_col: ‘3’, nb_filter: ‘64’, nb_row: ‘3’}
    class: Convolution2D
    name: Convolution2D_3
    x: 429.52
    y: 180
  • args: {activation: relu, nb_col: ‘3’, nb_filter: ‘32’, nb_row: ‘3’}
    class: Convolution2D
    name: Convolution2D_4
    x: 2
    y: 432
  • args: {}
    class: MaxPooling2D
    name: MaxPooling2D_1
    x: 11
    y: 559
  • args: {p: ‘0.25’}
    class: Dropout
    name: Dropout_1
    x: 13
    y: 662
  • args: {}
    class: MaxPooling2D
    name: MaxPooling2D_2
    x: 442.8
    y: 330
  • args: {p: ‘0.25’}
    class: Dropout
    name: Dropout_2
    x: 426.88
    y: 532.08
  • args: {}
    class: Flatten
    name: Flatten_1
    x: 846.6999999999999
    y: 91.12
  • args: {activation: relu, output_dim: ‘512’}
    class: Dense
    name: Dense_1
    x: 842.12
    y: 217.38000000000002
  • args: {p: ‘0.5’}
    class: Dropout
    name: Dropout_3
    x: 839.36
    y: 329.12
  • args: {activation: softmax, output_dim: ‘10’}
    class: Dense
    name: Dense_2
    x: 823.3
    y: 481.72
    params:
    advance_params: true
    batch_size: 32
    is_custom_loss: false
    loss_func: categorical_crossentropy
    num_epoch: 10
    optimizer: {decay: 1e-6, momentum: ‘0.9’, name: SGD, nesterov: true}
    project: Driver
  1. For image column, set Data Type as Image and Input & Output as InputPort0

  2. For Rating column, set Input & Output as OutputPort0

I think you still have dataset issue, since image is not getting displayed. This means that system is not able to access the image file as mentioned in the file path in train.csv.

Still The Problem not solved

For the Physical Location:

The Address on the Physical location (explorer) : E:\Tensor Flow R\District Driver\imgs\train

your train.csv should not contain ./img/train prefix in file paths.

All the paths in train.csv needs to be relative to the train.csv file. So replace them with “./cX/img_XXXX.jpg” format.

Ok thanks I’ll do and get back to you.

But Is the location of the (csv) file is correct?

Still Nothing Been Change the error still continued and Images didn’t displayed in the data tap, I did the prefix change as in the screenshot :thinking:

I asked my self Question, Do you think the problem Image does not display in the (Data Tab) related to GPU?
I Installed the Desktop version with CPU not GPU cuz I dont’t have NEVDA drive on my machine , please advise
Thank you

The answer not because It display the (Minset) Images without any problem

You have two location for the datasets. One is your host folder: E:\Tensor Flow R\District Driver\imgs\train and other one is the one which you uploaded in Deep Learning Studio.

Did you update train.csv in the host folder or did you update the folder inside the Deep Learning Studio?

Deep Learning Studio keeps the all the uploaded dataset in the <dls install location>\data\1\datasets. Your uploaded train dataset should be present inside that location. You can directly modify the train.csv there.

Also, image not getting displayed has nothing to do with GPU.

Regards

I didn’t understand your advise , could you re-expaline it precisely with images if you can?

You said you made the changes in train.csv. What is the location of updated train.csv ?

Is it E:\Tensor Flow R\District Driver\imgs\train?

OR

<DLS Install Location>\data\1\datasets\train ?

Thank you for your replay , Attached all the needed information , but In general the process of uploading is not clear in the video at least to me , I hope that you provide more documentation for this process.
Thank you again

In your video, the prefix written like this: ./xxxxxx/file.jpg , That what I understood

The Video Is Misleading :thinking::no_mouth: