|
161 | 161 | "source": [
|
162 | 162 | "`AutoDL` class accepts the following paramters:\n",
|
163 | 163 | "\n",
|
164 |
| - "- `data` (Required Paramter): Returned data object from `prepare_data` function in the previous step.\n", |
| 164 | + "- `data` (Required Parameter): The data object returned from the `prepare_data` function in the previous step.\n", |
165 | 165 | " \n",
|
166 |
| - "- `total_time_limit` (Optional parameter):\n", |
167 |
| - " The total time limit in hours for `AutoDL` to train and evaluate the networks. This parameter becomes important when time is the main constraint to the user. The `AutoDL` class calculates the number of chips that can be processed in the given time from the prepared databunch.\n", |
| 166 | + "- `total_time_limit` (Optional parameter): The total time limit in hours for the `AutoDL` to train and evaluate the networks. This parameter becomes important when time is the main constraint to the user. The `AutoDL` class calculates the number of chips that can be processed in the given time from the prepared databunch.\n", |
168 | 167 | " \n",
|
169 | 168 | " \n",
|
170 | 169 | "- `mode` (Optional Parameter): Can be \"basic\" or \"advanced\".\n",
|
171 | 170 | "\n",
|
172 | 171 | " - _basic_ : To to be used when the user wants to train all selected networks.\n",
|
173 |
| - " - _advanced_ : To be used when the user additionally wants to tune hyper parameters of two best performing models from basic mode.\n", |
| 172 | + " - _advanced_ : To be used when the user also wants to tune hyper parameters of the two best performing models from the basic mode.\n", |
174 | 173 | " \n",
|
175 | 174 | "\n",
|
176 | 175 | "- `networks` (Optional Parameter):\n",
|
177 |
| - " The list of models that will be used in the training process. If the user does not provides the parameter value the `AutoDL` class selects all the supported networks, however user can select one or multiple networks by passing the network name in a list.\n", |
| 176 | + " The list of models that will be used in the training process. If the user does not provide the parameter value, the `AutoDL` class selects all of the supported networks, however the user can select one or more networks by passing the network names in a list.\n", |
178 | 177 | "\n",
|
179 | 178 | " - _Supported Object Detection models_\n",
|
180 | 179 | " - SingleShotDetector, RetinaNet, FasterRCNN, YOLOv3, MMDetection\n",
|
|
0 commit comments