andreasjansson / train-dynamic-system

  • Public
  • 164 runs

Run andreasjansson/train-dynamic-system with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
code
string
None
target1
string
None
target2
string
None
width
integer
128
None
height
integer
128
None
training_steps
integer
1000
None
max_variables
integer
100
None
cycle_length
integer
20
None
loss_cycles
integer
4
None
total_cycles
integer
6
None
learning_rate
number
0.005
None
yield_every
integer
250
None
return_animation
boolean
True
None
timeout
integer
600
None
seed
integer
None
model_state
string
None
optimizer_state
string
None

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "object",
    "title": "ModelOutput",
    "required": [
      "visualization"
    ],
    "properties": {
      "animation": {
        "type": "string",
        "title": "Animation",
        "format": "uri"
      },
      "model_state": {
        "type": "string",
        "title": "Model State",
        "format": "uri"
      },
      "cycle_images": {
        "type": "array",
        "items": {
          "type": "string",
          "format": "uri"
        },
        "title": "Cycle Images"
      },
      "visualization": {
        "type": "string",
        "title": "Visualization",
        "format": "uri"
      },
      "optimizer_state": {
        "type": "string",
        "title": "Optimizer State",
        "format": "uri"
      },
      "historical_losses": {
        "type": "array",
        "items": {
          "type": "number"
        },
        "title": "Historical Losses"
      },
      "cycle_losses_target1": {
        "type": "array",
        "items": {
          "type": "number"
        },
        "title": "Cycle Losses Target1"
      },
      "cycle_losses_target2": {
        "type": "array",
        "items": {
          "type": "number"
        },
        "title": "Cycle Losses Target2"
      }
    }
  },
  "title": "Output",
  "x-cog-array-type": "iterator"
}