Open athus1990 opened 8 years ago
Are you progressed? Could you successfully train and test SegNet on Cityscapes database?
Yea.But it is not as great as training with camvid.
Did you actually get reasonable results from training. I am still getting an output which is majority of one label. How did you run the training? Did you just fine-tune from the VGG net?
yes the results were great! Just not great enough.I did start with Vgg16. Converted cityscapes Annotations-->similar to Camvids and then changed the number of classes.
Could you share the trained model on the Cityscapes dataset for evaluation purposes?
Sure.just give me an hour
Great!
Hey @athus1990 , would it be possible to share the model?
This issue can be closed now...
Hi athus1990,
I was trying to train the segnet with the cityscapes data set however i get the following error
Check failed: status == CUBLAS_STATUS_SUCCESS (11 vs. 0) CUBLAS_STATUS_MAPPING_ERROR
I believe this is due to the difference in annotations used by the city scapes data set.
Here you have said you have converted the cityscapes Annotations-->similar to Camvids.
Can you please let me know how did you do it. some script?
@athus1990 what is the mIoU about your model trained on Cityscapes, the loss does not seem to fall when the iterations increase.
Hi @alexgkendall , I trained segnet(non basic non Bayesian version ) on the Cityscapes dataset(44gb of 19k+ images and annotations that need to be converted to segnet annotations). However training it on cityscapes and testing it on a new test image does not produce the same "smooth" results as shown by webcam demo. I tried to show the difference here(excuse the color difference:red is road and purple is pavement and so on:
My soln(the road and pavements are not smooth,many miscalssifications):![image](https://cloud.githubusercontent.com/assets/7275643/14894000/85216826-0d3f-11e6-8468-95e3e689261a.png)
Your webdemo(testing on similar image of mine):![image](https://cloud.githubusercontent.com/assets/7275643/14894114/1d8a4196-0d40-11e6-89ba-a617c23d5b13.png)
However on camvid testimage:![image](https://cloud.githubusercontent.com/assets/7275643/14894157/591bfefc-0d40-11e6-84fa-0b31fa415c2e.png)
So here goes my question: 1)webdemo was trained on ~500 images it gives great results.I trained segnet with 19k+ images and 90000+ iterations and dint change anything else.Why am I not getting a smooth performance. Should it not do better. 2)Also the cityscapes dataset has a resolution of 1024x2048 which i rescaled to 360x480 for segnet. My test image which segnet has never trained on is 1080x1920 which i rescaled to 360x480.Does resolution matter? 3)Are you testing it differently to get a smoother performance.?All I am doing is similar to testcamvid.py in ur code:
image= cv2.resize(image, (input_shape[3], input_shape[2])) input_image = image.transpose((2, 0, 1)) input_image = input_image[(2, 1, 0), :, :] input_image = np.asarray([input_image])
out = net.forward_all(data=input_image) segmentation_ind = np.squeeze(net.blobs['argmax'].data) segmentation_ind_3ch = np.resize(segmentation_ind, (3, input_shape[2], input_shape[3])) segmentation_ind_3ch = segmentation_ind_3ch.transpose(1, 2, 0).astype(np.uint8) segmentation_rgb = np.zeros(segmentation_ind_3ch.shape, dtype=np.uint8) cv2.LUT(segmentation_ind_3ch, label_colours, segmentation_rgb) segmentation_rgb = segmentation_rgb.astype(float) / 255.0
Could you please help me understand this better?
also note: -the training began with vgg16 ILSVRC pretrained encoder
also pls find the training loss:![image](https://cloud.githubusercontent.com/assets/7275643/14895828/aa7e66e2-0d48-11e6-88a5-a66772dd0a25.png)