nicolasrosa

@lpqdao Hello Grace, I believe this is caused by the align_corners parameter from the tf.resize_images function.

No, about the black boxes. In my code, it's in several places: train.py, validation.py and test.py.

@a-jahani I've been using Monodepth's evaluation file. However, I'm not sure if I'm using the correct predicted images since their model predict disparities instead of depths. https://github.com/mrharicot/monodepth/blob/master/utils/evaluate_kitti.py

@Sunyx93 Are you predicting Depth (meters, log(meters)) or Disparities? Which dataset are you evaluating? KITTI Stereo 2015 (200 testing images) or KITTI RawData using the Eigen's split (697 testing images)?

Since you're predicting Depth in meters like me, I recommend you review the evaluation code checking if you're not using disparity information as ground truth. For instance, I had to...

@a-jahani Thanks for the information. We should had this conversation some weeks ago. I just submitted an article last week haha. It's too late now. I agree with you guys,...

1. Nice, this confirms what I was suspecting. The only problem is that, so far in the book, P = [X, Y, Z]^T has been used to represent the 3D...

If I remember, this value is the conversion value between the depth values (float, metric) and the values saved on the PNG (16-bits, int, [0, 65535]) from TUM Dataset.

Was this the value read directly from the 16-bit png image? In your case, I believe you already are in the metric system, I can do the calculation in millimeters...

```python from matplotlib import pyplot as plt import numpy as np def print_info(var): print(var.shape, var.dtype, np.min(var), np.max(var)) def main(): # --- Figure 1 fig, axes = plt.subplots(6,1) # Initial data...