Where is a list to the papers with all the benchmarks and models done to this data set?

https://www.quora.com/unanswered/What-is-the-leadership-board-the-the-CLEVER-dataset-in-Machine-Learning

• Is this repo compatible with blender 2.8? if not which version should I install? I recommend you to add this to the README file since this info is not included for now.

• Another question please: I saw json file example of generated image and under "pixel_coords" key there was a list of three values. What does the last value represent?

Hi,

I am noticing an inconsistency between the placement of the 3d objects in the scene and their corresponding 3d coordinates in the scene. For instance, to show some examples:

(1): (it looks like the z-axis in this plot corresponds to how close/far you are from the camera, e.g. 'small-cyclinder-brown' and 'small-sphere-gray' are at the top of the z-axis, and they are closest to the camera)

(2): (this contradicts (1) now, because the small red cylinder lies around the midpoint of the z-axis yet it's actually the furthest from the camera)

(3): (again, contradicts the previous images, because the gold sphere is closest to the camera but lies about the mid-point of the z-axis)

I have not generated the dataset myself from source, but if there is a discrepancy between the code and the dataset that is available online that may explain it. Or, if the 3d coordinates are not relative to the camera (e.g. the camera was randomly displaced prior to rendering). I tried looking at the code but I didn't find anything that appeared to be odd to me, but I am really not sure at this stage.

Thanks!

I am referring to the repository CLEVR IEP for training model. I followed the steps as in the TRAINING.md file but unfortunately the script breaks. In the file programs.py inside functions function_to_str, list_to_tree, tree_to_prefix, tree_to_postfix all tries to access the key cur['function'], which does not exist in any of the questions generated.

Does someone have the updated code for clevr-dataset-gen for questions generation, and if not how this could be tackled?

This is pull request was created automatically because we noticed your project was missing a Code of Conduct file.

Code of Conduct files facilitate respectful and constructive communities by establishing expected behaviors for project contributors.

This PR was crafted with love by Facebook's Open Source Team.

For my project I need to render images with fixed number of objects ( max_objects=min_objects =2 for now) and fix the locations of the objects in all the rendered scenes. Any thoughts on how to fix the location parameter?

First and foremost, it goes without saying, but great repo and dataset!

Moving on to the issue, I believe there's a slight error in the zeroeth template of compare_integer.json

Specifically, the zeroeth template (with indenting for legibility) is as follows:

    "constraints": [
      {
        "params": [
          1,
          3
        ],
        "type": "OUT_NEQ"
      }
    ],
    "nodes": [
      {
        "inputs": [],
        "type": "scene"
      },
      {
        "inputs": [
          0
        ],
        "side_inputs": [
          "<Z>",
          "<C>",
          "<M>",
          "<S>"
        ],
        "type": "filter_count"
      },
      {
        "inputs": [],
        "type": "scene"
      },
      {
        "inputs": [
          2
        ],
        "side_inputs": [
          "<Z2>",
          "<C2>",
          "<M2>",
          "<S2>"
        ],
        "type": "filter_count"
      },
      {
        "inputs": [
          1,
          3
        ],
        "type": "equal_integer"
      }
    ],
    "params": [
      {
        "name": "<Z>",
        "type": "Size"
      },
      {
        "name": "<C>",
        "type": "Color"
      },
      {
        "name": "<M>",
        "type": "Material"
      },
      {
        "name": "<S>",
        "type": "Shape"
      },
      {
        "name": "<Z2>",
        "type": "Size"
      },
      {
        "name": "<C2>",
        "type": "Color"
      },
      {
        "name": "<M2>",
        "type": "Material"
      },
      {
        "name": "<S2>",
        "type": "Shape"
      }
    ],
    "text": [
      "Are there an equal number of <Z> <C> <M> <S>s and <Z2> <C2> <M2> <S2>s?",
      "Are there the same number of <Z> <C> <M> <S>s and <Z2> <C2> <M2> <S2>s?",
      "Is the number of <Z> <C> <M> <S>s the same as the number of <Z2> <C2> <M2> <S2>s?"
    ]
  },

Note the constraint is OUT_NEQ between nodes 1 and 3. However, nodes 1 and 3 are filter_count nodes rather than filter nodes, so the constraint is that the counts (rather than the objects found) must differ. Consequently, the answer is always false (there cannot be an equal number of objects, because our constraint forces the object count to differ). I threw together a quick script to try and check the answers in the CLEVR training set, and I believe it supports my conclusions.

It's not a serious issue, but it confused me and took me a while to figure out what was going on -- I hope this spares someone else some debugging time. Cheers!

https://github.com/facebookresearch/clevr-dataset-gen/blob/f0ce2c81750bfae09b5bf94d009f42e055f2cb3a/image_generation/render_images.py#L411

https://github.com/facebookresearch/clevr-dataset-gen/blob/f0ce2c81750bfae09b5bf94d009f42e055f2cb3a/image_generation/utils.py#L104

I think there is a mistake here. When I tried to use the object rotation, I found that the object did not rotate much. After I debug, I find that the angle here is incorrect. This angle should be radians, not angles.

I hope everyone can understand this problem. After all, this problem has caused me a lot of trouble.

Do you have thinking about to add background by HDRI data. I have try to do this, but it seems like something wrong. maybe because the camera is too close to the HDRI world scene. So, is there any example to replace the pure background with other images such like COCO

I tried adding different shapes that I created into the dataset, but to render some new images, but I get an error: " bpy_prop_collection[key]: Key "Polygon not found' " I was able to add a torus and a cone with no issues, but not anything else. (Like a cube that isn't smooth) Could you explain to me why this is an issue?