Replicating Results

Numerous publications in the larger Dex-Net project utilize GQ-CNNs, particularly Dex-Net 2.0, Dex-Net 2.1, Dex-Net 3.0, Dex-Net 4.0, and FC-GQ-CNN. One of the goals of the gqcnn library is to provide the necessary code and instructions for replicating the results of these papers. Thus, we have provided a number of replication scripts under the scripts/ directory.

There are two ways to replicate results:

  1. Use a pre-trained model: Download a pre-trained GQ-CNN model and run an example policy.

  2. Train from scratch: Download the raw dataset, train a GQ-CNN model, and run an example policy using the model you just trained.

We highly encourage method 1. Note that method 2 is computationally expensive as training takes roughly 24 hours on a Nvidia Titan Xp GPU. Furthermore, the raw datasets are fairly large in size.

Please keep in mind that GQ-CNN models are sensitive to the following parameters used during dataset generation:
  1. The robot gripper

  2. The depth camera

  3. The distance between the camera and workspace.

As a result, we cannot guarantee performance of our pre-trained models on other physical setups.

For more information about the pre-trained models and sample inputs for the example policy, see Pre-trained Models and Sample Inputs.

Using a Pre-trained Model

First download the pre-trained models.

$ ./scripts/downloads/models/download_models.sh

Dex-Net 2.0

Evaluate the pre-trained GQ-CNN model.

$ ./scripts/policies/run_all_dex-net_2.0_examples.sh

Dex-Net 2.1

Evaluate the pre-trained GQ-CNN model.

$ ./scripts/policies/run_all_dex-net_2.1_examples.sh

Dex-Net 3.0

Evaluate the pre-trained GQ-CNN model.

$ ./scripts/policies/run_all_dex-net_3.0_examples.sh

Dex-Net 4.0

To evaluate the pre-trained parallel jaw GQ-CNN model.

$ ./scripts/policies/run_all_dex-net_4.0_pj_examples.sh

To evaluate the pre-trained suction GQ-CNN model.

$ ./scripts/policies/run_all_dex-net_4.0_suction_examples.sh

FC-GQ-CNN

To evaluate the pre-trained parallel jaw FC-GQ-CNN model.

$ ./scripts/policies/run_all_dex-net_4.0_fc_pj_examples.sh

To evaluate the pre-trained suction FC-GQ-CNN model.

$ ./scripts/policies/run_all_dex-net_4.0_fc_suction_examples.sh

Training from Scratch

Dex-Net 2.0

First download the appropriate dataset.

$ ./scripts/downloads/datasets/download_dex-net_2.0.sh

Then train a GQ-CNN from scratch.

$ ./scripts/training/train_dex-net_2.0.sh

Finally, evaluate the trained GQ-CNN.

$ ./scripts/policies/run_all_dex-net_2.0_examples.sh

Dex-Net 2.1

First download the appropriate dataset.

$ ./scripts/downloads/datasets/download_dex-net_2.1.sh

Then train a GQ-CNN from scratch.

$ ./scripts/training/train_dex-net_2.1.sh

Finally, evaluate the trained GQ-CNN.

$ ./scripts/policies/run_all_dex-net_2.1_examples.sh

Dex-Net 3.0

First download the appropriate dataset.

$ ./scripts/downloads/datasets/download_dex-net_3.0.sh

Then train a GQ-CNN from scratch.

$ ./scripts/training/train_dex-net_3.0.sh

Finally, evaluate the trained GQ-CNN.

$ ./scripts/policies/run_all_dex-net_3.0_examples.sh

Dex-Net 4.0

To replicate the Dex-Net 4.0 parallel jaw results, first download the appropriate dataset.

$ ./scripts/downloads/datasets/download_dex-net_4.0_pj.sh

Then train a GQ-CNN from scratch.

$ ./scripts/training/train_dex-net_4.0_pj.sh

Finally, evaluate the trained GQ-CNN.

$ ./scripts/policies/run_all_dex-net_4.0_pj_examples.sh

To replicate the Dex-Net 4.0 suction results, first download the appropriate dataset.

$ ./scripts/downloads/datasets/download_dex-net_4.0_suction.sh

Then train a GQ-CNN from scratch.

$ ./scripts/training/train_dex-net_4.0_suction.sh

Finally, evaluate the trained GQ-CNN.

$ ./scripts/policies/run_all_dex-net_4.0_suction_examples.sh

FC-GQ-CNN

To replicate the FC-GQ-CNN parallel jaw results, first download the appropriate dataset.

$ ./scripts/downloads/datasets/download_dex-net_4.0_fc_pj.sh

Then train a FC-GQ-CNN from scratch.

$ ./scripts/training/train_dex-net_4.0_fc_pj.sh

Finally, evaluate the trained FC-GQ-CNN.

$ ./scripts/policies/run_all_dex-net_4.0_fc_pj_examples.sh

To replicate the FC-GQ-CNN suction results, first download the appropriate dataset.

$ ./scripts/downloads/datasets/download_dex-net_4.0_fc_suction.sh

Then train a FC-GQ-CNN from scratch.

$ ./scripts/training/train_dex-net_4.0_fc_suction.sh

Finally, evaluate the trained FC-GQ-CNN.

$ ./scripts/policies/run_all_dex-net_4.0_fc_suction_examples.sh