@hoff97/tensor-js
Version:
PyTorch like deep learning inferrence library
45 lines • 2.03 kB
JavaScript
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
import { OnnxNode } from '../node';
export class UnsqueezeNode extends OnnxNode {
constructor(attributes, inputs, outputs, constants, onnxVersion, mode) {
super(attributes, inputs, outputs, constants, onnxVersion, mode);
if (onnxVersion < 13) {
this.axes = this.getAttributeInts('axes');
}
}
forward(inputs) {
return __awaiter(this, void 0, void 0, function* () {
const x = inputs[0];
if (this.onnxVersion < 13 && this.axes !== undefined) {
const currShape = x.getShape();
const newShape = [];
let axIx = 0;
for (let i = 0; i < currShape.length; i++) {
if (axIx < this.axes.length && this.axes[axIx] === i) {
newShape.push(1);
axIx++;
}
newShape.push(currShape[i]);
}
if (this.axes[this.axes.length - 1] === currShape.length) {
newShape.push(1);
}
return [x.reshape(newShape)];
}
throw new Error(`Unsqueeze with onnx version ${this.onnxVersion} not yet implemented`);
});
}
getType() {
return 'Unsqueeze';
}
delete() { }
}
//# sourceMappingURL=unsqueeze.js.map