Comments (6)
The warning message is due to the 11 empty classes in computing scores but I don't think they caused the crash. Is there any other message?
from deeplab-pytorch.
I pasted the whole message. From the call of the function to the end.
from deeplab-pytorch.
I guess this has produced data/models/deeplab_resnet101/cocostuff10k/checkpoint_final.json
. Could you check the results in it?
from deeplab-pytorch.
This is the content of checkpoint_final.json
{
"Class IoU": {
"0": 0.21776031472603485,
"1": 0.0075313480134847,
"2": 0.010529395062124174,
"3": 0.1142311820758051,
"4": 0.15680853247422566,
"5": 0.1553699686097208,
"6": 0.07940892360365252,
"7": 0.0239045048910893,
"8": 0.05438100973147119,
"9": 0.0,
"10": 0.03285660560156375,
"11": NaN,
"12": 0.16322006007399154,
"13": 0.0,
"14": 0.00028673932541516047,
"15": 0.030766132922782626,
"16": 0.0716802555359043,
"17": 0.0014689395178156346,
"18": 0.010782807472347262,
"19": 0.011346585851735685,
"20": 0.026164698597558583,
"21": 0.06877453791913118,
"22": 0.00143959185348306,
"23": 0.3507167152475488,
"24": 0.20333232073456453,
"25": NaN,
"26": 0.0,
"27": 0.0701295842848103,
"28": NaN,
"29": NaN,
"30": 0.0,
"31": 0.0,
"32": 0.000381445775248638,
"33": 0.0,
"34": 0.0,
"35": 0.0,
"36": 0.0,
"37": 0.019206799118172826,
"38": 0.0,
"39": 0.0,
"40": 0.0,
"41": 0.0,
"42": 0.0,
"43": 0.001446426652141677,
"44": NaN,
"45": 0.0,
"46": 0.0,
"47": 0.0,
"48": 0.0,
"49": 0.0,
"50": 0.017704600886703697,
"51": 0.04472283690999325,
"52": 0.000587367305130152,
"53": 0.028867061857040327,
"54": 0.009565165586586263,
"55": 0.06361377289888306,
"56": 0.021537571664313297,
"57": 0.00463431971209009,
"58": 0.3138594939238026,
"59": 0.03272228486405431,
"60": 0.03695458825309139,
"61": 0.00648648715888255,
"62": 0.007724832097666072,
"63": 0.007808366769259286,
"64": 0.01715783065240214,
"65": NaN,
"66": 0.14126218274588456,
"67": NaN,
"68": NaN,
"69": 0.005970357292199043,
"70": NaN,
"71": 0.06696863941210839,
"72": 0.02489182905217069,
"73": 0.0,
"74": 0.0,
"75": 0.01797214196943041,
"76": 0.0,
"77": 0.0009338764960953866,
"78": 0.009952751886211229,
"79": 0.0,
"80": 1.5043385122693849e-05,
"81": 0.0005410314977572538,
"82": NaN,
"83": 0.001031146877809695,
"84": 0.004699186494319448,
"85": 0.00013389031705227078,
"86": 0.0,
"87": 0.0,
"88": 0.0,
"89": 0.0,
"90": NaN,
"91": 0.056369384428375136,
"92": 0.0,
"93": 0.0,
"94": 0.0,
"95": 0.14702148817247565,
"96": 0.005678723641883982,
"97": 0.01592615198746547,
"98": 0.0,
"99": 0.0,
"100": 0.0005946183927692746,
"101": 0.06298477004626131,
"102": 0.0,
"103": 0.0,
"104": 0.0,
"105": 0.3605711459480303,
"106": 0.0004574677891267208,
"107": 0.05640430009453367,
"108": 0.001547697297915208,
"109": 0.026453185264671046,
"110": 0.10525516143999408,
"111": 5.762372264522046e-05,
"112": 0.055451798506117055,
"113": 0.0,
"114": 2.1102500118701564e-05,
"115": 0.0,
"116": 0.0024931008309868443,
"117": 0.13713604858903805,
"118": 0.00567750255460293,
"119": 0.0,
"120": 0.05980029593124254,
"121": 0.0,
"122": 0.0014643086267089461,
"123": 0.45892172781275736,
"124": 0.030677207081064143,
"125": 0.016552556139865848,
"126": 0.04505122597867671,
"127": 0.020425630349294472,
"128": 0.0,
"129": 0.0009288202197017058,
"130": 0.0,
"131": 0.001113178098512102,
"132": 0.0004951156107957748,
"133": 0.0,
"134": 0.03927793738220278,
"135": 0.0,
"136": 0.0,
"137": 0.0005063789276919827,
"138": 0.0,
"139": 0.040448710375644924,
"140": 0.0,
"141": 0.006495504728168809,
"142": 0.0,
"143": 0.0,
"144": 0.33246302891435864,
"145": 0.0003081183754549277,
"146": 0.08061405889293899,
"147": 0.0014805826043085284,
"148": 0.2506697355571653,
"149": 0.0007117219584953721,
"150": 0.0,
"151": 0.0,
"152": 0.0,
"153": 0.1448627984788912,
"154": 0.32208121809705126,
"155": 0.0,
"156": 0.5189216159996083,
"157": 0.0,
"158": 0.38734605921487736,
"159": NaN,
"160": 0.0,
"161": 0.0,
"162": 0.002990462371489746,
"163": 0.0011291770328260575,
"164": 0.000993882897356723,
"165": 0.0,
"166": 0.0,
"167": 0.0,
"168": 0.3351500439016227,
"169": 0.005048672073477044,
"170": 0.1110446677081931,
"171": 0.0,
"172": 0.25354950540678434,
"173": 0.0,
"174": 0.0029059427391312782,
"175": 0.009869441948219797,
"176": 0.0032671081677704194,
"177": 0.03667632471765454,
"178": NaN,
"179": 0.009519428126548234,
"180": 0.07582460584369584,
"181": 0.0
},
"Frequency Weighted IoU": 0.17846328817680418,
"Mean Accuracy": 0.07708677265415062,
"Mean IoU": 0.043916758302574806,
"Pixel Accuracy": 0.3326036556498822
}
from deeplab-pytorch.
Hmm, no-message crashing is strange to me. Could you investigate where the code crashes?
from deeplab-pytorch.
OK. I'll have a look. Thanks.
from deeplab-pytorch.
Related Issues (20)
- only 20% mIou HOT 4
- The results of VOC2012 val dataset HOT 2
- cannot find setup_voc12.sh
- how to do the augmentation for training? HOT 2
- what do we mean by unary? HOT 2
- custom dataset HOT 2
- get_dataset HOT 2
- the pre-trained model HOT 2
- The training result is poor after using the weak supervision data set HOT 4
- How to convert the generated npy file into an image HOT 4
- A simple question about test on VOC HOT 1
- COCO number of classes HOT 4
- Question VOC HOT 1
- How to train on COCO2014 dataset HOT 1
- How to train on the coco-stuff datasets? HOT 1
- Training Deeplab-pytorch on VOC2012 raises metaclass conflict error with TensorFlow 1.10.0 and ANTLR downgrade to 4.8
- Visualize the segmented picture of the validation set HOT 1
- Big loss
- Extract Feature map HOT 2
- How to refer to your work? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deeplab-pytorch.